A gentle introduction to deep learning for graphs
The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and atte...
Saved in:
| Published in | Neural networks Vol. 129; pp. 203 - 221 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
01.09.2020
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0893-6080 1879-2782 1879-2782 |
| DOI | 10.1016/j.neunet.2020.06.006 |
Cover
Loading…
| Abstract | The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is a tutorial introduction to the field of deep learning for graphs. It favors a consistent and progressive presentation of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. Moreover, it introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. We complement the methodological exposition with a discussion of interesting research challenges and applications in the field. |
|---|---|
| AbstractList | The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is a tutorial introduction to the field of deep learning for graphs. It favors a consistent and progressive presentation of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. Moreover, it introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. We complement the methodological exposition with a discussion of interesting research challenges and applications in the field.The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is a tutorial introduction to the field of deep learning for graphs. It favors a consistent and progressive presentation of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. Moreover, it introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. We complement the methodological exposition with a discussion of interesting research challenges and applications in the field. The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning community. The snap increase in the amount and breadth of related research has come at the price of little systematization of knowledge and attention to earlier literature. This work is a tutorial introduction to the field of deep learning for graphs. It favors a consistent and progressive presentation of the main concepts and architectural aspects over an exposition of the most recent literature, for which the reader is referred to available surveys. The paper takes a top-down view of the problem, introducing a generalized formulation of graph representation learning based on a local and iterative approach to structured information processing. Moreover, it introduces the basic building blocks that can be combined to design novel and effective neural models for graphs. We complement the methodological exposition with a discussion of interesting research challenges and applications in the field. |
| Author | Bacciu, Davide Errica, Federico Micheli, Alessio Podda, Marco |
| Author_xml | – sequence: 1 givenname: Davide surname: Bacciu fullname: Bacciu, Davide email: bacciu@di.unipi.it – sequence: 2 givenname: Federico surname: Errica fullname: Errica, Federico email: federico.errica@phd.unipi.it – sequence: 3 givenname: Alessio surname: Micheli fullname: Micheli, Alessio email: micheli@di.unipi.it – sequence: 4 givenname: Marco surname: Podda fullname: Podda, Marco email: marco.podda@di.unipi.it |
| BookMark | eNqFkE1LAzEURYMo2Fb_gYtZupnxJZlmEhdCKX5BwY2uQybzpqZMk5qkgv_eKXXlQuHB3dxz4Z0pOfXBIyFXFCoKVNxsKo97j7liwKACUQGIEzKhslElayQ7JROQipcCJJyTaUobGBuy5hNCF8UafR6wcD7H0O1tdsEXORQd4q4Y0ETv_LroQyzW0eze0wU5682Q8PInZ-Tt4f51-VSuXh6fl4tVabmc57KjoqetZAC2lqpvFefQ9obNW-Qd9ApEo0zPmDBQd0wJSSUgtE0zZy1HaPiMXB93dzF87DFlvXXJ4jAYj2GfNKvpnCnFx5uR22PVxpBSxF5bl83hkRyNGzQFffCkN_roSR88aRB6tDDC9S94F93WxK__sLsjhqODT4dRJ-vQW-xcRJt1F9zfA9_VBYUi |
| CitedBy_id | crossref_primary_10_1007_s10209_024_01123_0 crossref_primary_10_1016_j_bdr_2024_100494 crossref_primary_10_1016_j_aei_2024_103050 crossref_primary_10_1016_j_inffus_2025_102996 crossref_primary_10_1109_JOE_2023_3314090 crossref_primary_10_3233_IA_210121 crossref_primary_10_1016_j_neucom_2022_04_072 crossref_primary_10_1016_j_image_2020_116080 crossref_primary_10_1021_acs_jpca_4c04121 crossref_primary_10_1016_j_neucom_2025_129635 crossref_primary_10_1093_insilicoplants_diad001 crossref_primary_10_1063_5_0177738 crossref_primary_10_1109_TNNLS_2020_3025110 crossref_primary_10_1088_1361_6560_ad8c94 crossref_primary_10_1016_j_inffus_2023_102186 crossref_primary_10_1016_j_knosys_2021_108105 crossref_primary_10_1109_TGRS_2021_3120218 crossref_primary_10_1016_j_neucom_2023_126506 crossref_primary_10_1109_TNNLS_2022_3220548 crossref_primary_10_1016_j_neucom_2023_126900 crossref_primary_10_1016_j_neunet_2021_02_005 crossref_primary_10_1016_j_ymssp_2020_107144 crossref_primary_10_1016_j_ymssp_2021_108653 crossref_primary_10_1016_j_atech_2023_100172 crossref_primary_10_5937_fme2203393B crossref_primary_10_1016_j_segan_2024_101304 crossref_primary_10_1016_j_ymssp_2021_107692 crossref_primary_10_1016_j_neucom_2024_127861 crossref_primary_10_1016_j_tws_2024_112157 crossref_primary_10_3390_app12157548 crossref_primary_10_1007_s10462_024_10918_9 crossref_primary_10_1109_TAI_2021_3133818 crossref_primary_10_1007_s12206_024_0702_z crossref_primary_10_1016_j_ymssp_2024_111761 crossref_primary_10_3389_frai_2022_824655 crossref_primary_10_1109_TCBB_2022_3170365 crossref_primary_10_1109_MGRS_2024_3393010 crossref_primary_10_1109_ACCESS_2023_3323220 crossref_primary_10_1016_j_neunet_2021_05_031 crossref_primary_10_1093_bib_bbae027 crossref_primary_10_2174_1574893617666220513114917 crossref_primary_10_1093_bib_bbaf074 crossref_primary_10_3389_fmolb_2021_637396 crossref_primary_10_1016_j_sigpro_2024_109570 crossref_primary_10_3390_bioengineering8020021 crossref_primary_10_1145_3495161 crossref_primary_10_1371_journal_pcbi_1010718 crossref_primary_10_1039_D1CP01656C crossref_primary_10_1016_j_neunet_2023_10_050 crossref_primary_10_1016_j_cviu_2023_103744 crossref_primary_10_1016_j_jrmge_2024_09_034 crossref_primary_10_1007_s13042_024_02124_4 crossref_primary_10_3390_s22176482 crossref_primary_10_1109_TSMC_2023_3287655 crossref_primary_10_1080_13658816_2023_2168006 crossref_primary_10_3390_s24124022 crossref_primary_10_1016_j_health_2024_100310 crossref_primary_10_1016_j_neucom_2022_06_050 crossref_primary_10_1016_j_nicl_2024_103568 crossref_primary_10_3389_frobt_2022_840058 crossref_primary_10_1016_j_engappai_2024_109895 crossref_primary_10_1016_j_autcon_2021_103847 crossref_primary_10_26599_BDMA_2023_9020014 crossref_primary_10_1016_j_neunet_2024_106484 crossref_primary_10_1016_j_neunet_2024_106125 crossref_primary_10_1007_s11063_021_10576_w crossref_primary_10_1016_j_compmedimag_2024_102396 crossref_primary_10_1007_s00521_020_05529_8 crossref_primary_10_1016_j_neucom_2021_05_110 crossref_primary_10_1109_TNNLS_2024_3374464 crossref_primary_10_1109_TNNLS_2023_3267902 crossref_primary_10_1016_j_inffus_2024_102708 crossref_primary_10_1088_1742_6596_2363_1_012003 crossref_primary_10_1097_CM9_0000000000003387 crossref_primary_10_1109_ACCESS_2021_3124477 crossref_primary_10_1109_TNNLS_2023_3274565 crossref_primary_10_1016_j_neunet_2022_03_008 crossref_primary_10_1109_TNNLS_2022_3184967 crossref_primary_10_3390_electronics13245060 crossref_primary_10_1016_j_jvcir_2024_104167 crossref_primary_10_1007_s11235_024_01148_z crossref_primary_10_1016_j_neucom_2022_05_001 crossref_primary_10_1016_j_isci_2024_110041 crossref_primary_10_1007_s10618_021_00779_z crossref_primary_10_1016_j_neucom_2023_126948 crossref_primary_10_1093_bioinformatics_btad678 crossref_primary_10_1016_j_engappai_2023_106180 crossref_primary_10_1038_s41597_022_01870_w crossref_primary_10_1016_j_neunet_2022_07_035 crossref_primary_10_1109_TNNLS_2022_3171398 crossref_primary_10_1109_LRA_2022_3144520 crossref_primary_10_1021_acs_jpca_2c02614 crossref_primary_10_1109_TSIPN_2020_3046237 crossref_primary_10_1093_bib_bbae307 crossref_primary_10_1109_TNSE_2023_3330450 crossref_primary_10_1109_ACCESS_2020_3037118 crossref_primary_10_1016_j_neunet_2023_08_002 crossref_primary_10_1109_TPWRS_2022_3195301 crossref_primary_10_1371_journal_pone_0303889 crossref_primary_10_1109_TNNLS_2024_3379735 crossref_primary_10_1109_TAI_2024_3443783 crossref_primary_10_3390_su14137965 crossref_primary_10_1038_s42256_023_00609_5 crossref_primary_10_1016_j_neucom_2022_08_022 crossref_primary_10_1016_j_neunet_2023_04_029 crossref_primary_10_1145_3580516 crossref_primary_10_1515_sagmb_2021_0087 crossref_primary_10_1093_bioinformatics_btac478 crossref_primary_10_1016_j_neucom_2021_04_131 crossref_primary_10_1109_ACCESS_2022_3233036 crossref_primary_10_1021_jacs_4c04670 crossref_primary_10_1109_TPAMI_2021_3073504 crossref_primary_10_1371_journal_pcbi_1009531 crossref_primary_10_1007_s40747_024_01344_z crossref_primary_10_1007_s00521_024_09655_5 crossref_primary_10_21105_joss_05713 crossref_primary_10_1016_j_inffus_2021_09_004 crossref_primary_10_1016_j_epsr_2024_111163 crossref_primary_10_1038_s41598_022_25800_3 crossref_primary_10_1016_j_neucom_2024_127965 crossref_primary_10_1016_j_neunet_2024_106207 crossref_primary_10_1088_2632_2153_aca23e crossref_primary_10_1016_j_softx_2022_101061 crossref_primary_10_1007_s11063_022_10917_3 crossref_primary_10_1109_LCSYS_2023_3344286 crossref_primary_10_1038_s42256_020_0204_3 crossref_primary_10_1109_TETC_2023_3238963 crossref_primary_10_1080_00949655_2021_1921777 crossref_primary_10_1007_s10462_024_10931_y crossref_primary_10_1109_ACCESS_2021_3098417 crossref_primary_10_1109_TNNLS_2022_3165618 crossref_primary_10_1016_j_neunet_2023_05_048 |
| Cites_doi | 10.1007/s13748-018-0160-x 10.1016/j.neucom.2004.01.008 10.1093/bioinformatics/17.1.107 10.24963/ijcai.2018/505 10.1016/j.acha.2010.04.005 10.1109/72.712151 10.1007/s10115-007-0103-5 10.3115/v1/D14-1179 10.1214/aoms/1177706098 10.24963/ijcai.2019/563 10.1609/aaai.v32i1.11604 10.1162/neco.1997.9.8.1735 10.1109/TNN.2003.810735 10.1609/aaai.v32i1.11782 10.1186/s13321-019-0396-x 10.1016/j.neunet.2004.06.009 10.1109/TNN.2008.2005605 10.1109/TNNLS.2018.2804443 10.1016/j.artint.2014.08.003 10.1609/aaai.v32i1.11872 10.1162/0899766053491878 10.1109/TSMCB.2005.846635 10.1609/aaai.v33i01.33013558 10.1609/aaai.v33i01.33011110 10.1109/TNNLS.2012.2222044 10.1016/j.neucom.2008.12.021 10.24963/ijcai.2019/366 10.18653/v1/W18-5101 10.1016/j.knosys.2019.105020 10.1109/CVPR.2017.11 10.1007/BF00994018 10.1007/978-3-030-01418-6_41 10.1109/72.279181 10.1186/s40649-019-0069-y 10.1109/TNN.2009.2015974 10.1016/j.patcog.2018.07.023 10.18653/v1/P18-1026 10.1109/TNN.2004.837783 10.1093/bioinformatics/bty294 10.1023/A:1008368105614 10.1093/bioinformatics/bti1007 10.1609/aaai.v34i04.5803 10.1093/bioinformatics/btz307 10.3115/v1/P15-1150 10.1145/3326362 10.18653/v1/D17-1159 10.1109/TNNLS.2018.2803523 10.1109/5.58325 10.1007/BF02551274 10.1016/S0022-2836(03)00628-4 10.1609/aimag.v29i3.2157 10.1016/j.neunet.2005.07.009 10.1007/978-3-030-01228-1_25 10.7551/mitpress/7503.003.0205 10.1016/j.neucom.2018.05.095 10.1109/MSP.2017.2693418 10.2174/138161207780765981 10.1007/s11222-007-9033-z 10.1109/72.572108 10.1109/TNN.2008.2010350 10.1016/j.knosys.2013.03.012 10.24963/ijcai.2018/439 10.1023/A:1007649326333 10.18653/v1/N18-2078 10.1109/TPAMI.2007.1115 10.1021/jm00106a046 |
| ContentType | Journal Article |
| Copyright | 2020 Elsevier Ltd Copyright © 2020 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2020 Elsevier Ltd – notice: Copyright © 2020 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION 7X8 |
| DOI | 10.1016/j.neunet.2020.06.006 |
| DatabaseName | CrossRef MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 221 |
| ExternalDocumentID | 10_1016_j_neunet_2020_06_006 S0893608020302197 |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH 7X8 EFKBS |
| ID | FETCH-LOGICAL-c385t-d16f1b8200c489fb9330bfa25be3d0f90679af226a04d2968180e0b7752b3e073 |
| IEDL.DBID | .~1 |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Thu Sep 04 17:51:42 EDT 2025 Tue Jul 01 01:24:36 EDT 2025 Thu Apr 24 22:51:43 EDT 2025 Fri Feb 23 02:46:21 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Learning for structured data Graph neural networks Deep learning for graphs |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c385t-d16f1b8200c489fb9330bfa25be3d0f90679af226a04d2968180e0b7752b3e073 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | http://hdl.handle.net/11568/1045719 |
| PQID | 2415299399 |
| PQPubID | 23479 |
| PageCount | 19 |
| ParticipantIDs | proquest_miscellaneous_2415299399 crossref_citationtrail_10_1016_j_neunet_2020_06_006 crossref_primary_10_1016_j_neunet_2020_06_006 elsevier_sciencedirect_doi_10_1016_j_neunet_2020_06_006 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | September 2020 2020-09-00 20200901 |
| PublicationDateYYYYMMDD | 2020-09-01 |
| PublicationDate_xml | – month: 09 year: 2020 text: September 2020 |
| PublicationDecade | 2020 |
| PublicationTitle | Neural networks |
| PublicationYear | 2020 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | (pp. 609–618). De Cao, Kipf (b27) 2018 (pp. 412–422). Cho, Kyunghyun, van Merrienboer, Bart, Gülçehre, Çaglar, Bahdanau, Dzmitry, Bougares, Fethi, & Schwenk, Holger, et al. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Macskassy, Provost (b83) 2007; 8 Perozzi, Al-Rfou, Skiena (b95) 2014 You, Jiaxuan, Ying, Rex, Ren, Xiang, Hamilton, William L., & Leskovec, Jure (2018). GraphRNN: Generating realistic graphs with deep auto-regressive models. In Ribeiro, Saverese, Figueiredo (b98) 2017 (pp. 1601–1608). (pp. 1556–1566). Simonovsky, Martin, & Komodakis, Nikos GraphVAE: Towards generation of small graphs using variational autoencoders. In Zaheer, Manzil, Kottur, Satwik, Ravanbakhsh, Siamak, Poczos, Barnabas, Salakhutdinov, Ruslan R., & Smola, Alexander J. (2017). Deep sets. In Debnath, Lopez de Compadre, Debnath, Shusterman, Hansch (b28) 1991; 34 Mishra, Pushkar, Yannakoudakis, Helen, & Shutova, Ekaterina (2018). Neural character-based composition models for abuse detection. In Namata, Galileo Mark, London, Ben, Getoor, Lise, & Huang, Bert (2012). Query-driven active surveying for collective classification. In Tolstikhin, Ilya, Bousquet, Olivier, Gelly, Sylvain, & Schoelkopf, Bernhard (2018). Wasserstein auto-encoders. In Hammer, Micheli, Sperduti, Strickert (b58) 2004; 17 Vaswani, Ashish, Shazeer, Noam, Parmar, Niki, Uszkoreit, Jakob, Jones, Llion, & Gomez, Aidan N., et al. (2017). Attention is all you need. In Zhang, Cui, Zhu (b142) 2018 Gallicchio, Micheli (b44) 2010 (pp. 1110–1117). Gallicchio, Claudio, & Micheli, Alessio (2020). Fast and deep graph neural networks. In Sperduti, Starita (b113) 1997; 8 Errica, Federico, Podda, Marco, Bacciu, Davide, & Micheli, Alessio (2020). A fair comparison of graph neural networks for graph classification. In LeCun, Bengio (b75) 1995; 3361 (pp. 7795–7804). Grover, Leskovec (b50) 2016 Liu, Qi, Allamanis, Miltiadis, Brockschmidt, Marc, & Gaunt, Alexander (2018). Constrained graph variational autoencoders for molecule design. In (pp. 3700–3710). (pp. 2635–2641). Bruna, Joan, Zaremba, Wojciech, Szlam, Arthur, & LeCun, Yann (2014). Spectral networks and locally connected networks on graphs. In Hagenbuchner, Sperduti, Tsoi (b53) 2009; 72 (pp. 488–495). Zambon, Alippi, Livi (b140) 2018; 29 Dobson, Doig (b31) 2003; 330 Feng, Yifan, You, Haoxuan, Zhang, Zizhao, Ji, Rongrong, & Gao, Yue (2019). Hypergraph neural networks. In Yin, Li, Zhang, Lu (b134) 2019; 185 Bacciu, Errica, Micheli (b3) 2018 . Cortes, Vapnik (b25) 1995; 20 Socher, Richard, Lin, Cliff C., Manning, Chris, & Ng, Andrew Y. (2011). Parsing natural scenes and natural language with recursive neural networks. In Hammer, Micheli, Sperduti (b56) 2005; 17 Xu, Keyulu, Hu, Weihua, Leskovec, Jure, & Jegelka, Stefanie (2019). How powerful are graph neural networks? In Yang, Liang, Kang, Zesheng, Cao, Xiaochun, Jin, Di, Yang, Bo, & Guo, Yuanfang Topology optimization based graph convolutional network. In Chapelle, Schölkopf, Zien (b22) 2006; 20 Erdős, Rényi (b33) 1960; 5 (pp. 273–283). Ivanov, Sergey, & Burnaev, Evgeny (2018). Anonymous walk embeddings. In (pp. 3693–3702). (pp. 486–492). Bobadilla, Ortega, Hernando, Gutiérrez (b13) 2013; 46 Jiang, Jianwen, Wei, Yuxuan, Feng, Yifan, Cao, Jingxuan, & Gao, Yue (2019). Dynamic hypergraph neural networks. In (pp. 1506–1515). Fey, Lenssen (b39) 2019 (pp. 1724–1734). Duvenaud, David K., Maclaurin, Dougal, Iparraguirre, Jorge, Bombarelli, Rafael, Hirzel, Timothy, & Aspuru-Guzik, Alan, et al. (2015). Convolutional networks on graphs for learning molecular fingerprints. In Jin, Wengong, Barzilay, Regina, & Jaakkola, Tommi S. (2018). Junction tree variational autoencoder for molecular graph generation. In Wang, Sun, Liu, Sarma, Bronstein, Solomon (b126) 2019; 38 Calandriello, Daniele, Koutis, Ioannis, Lazaric, Alessandro, & Valko, Michal (2018). Improved large-scale graph learning through ridge spectral sparsification. In (pp. 3558–3565). (pp. 2434–2444). Bondy, Murty (b15) 1976 (pp. 3844–3852). Lee, Junhyun, Lee, Inyeop, & Kang, Jaewoo (2019). Self-attention graph pooling. In Yanardag, Vishwanathan (b132) 2015 Lovász (b81) 1993; 2 Zhang, Tong, Xu, Maciejewski (b144) 2019; 6 (pp. 2672–2680). Frederik Diehl, Brunner, Knoll (b42) 2019 (pp. 1–10). Shervashidze, Nino, Vishwanathan, SVN, Petri, Tobias, Mehlhorn, Kurt, & Borgwardt, Karsten (2009). Efficient graphlet kernels for large graph comparison. In (pp. 5453–5462). Zhang, Muhan, Cui, Zhicheng, Neumann, Marion, & Chen, Yixin (2018). An end-to-end deep learning architecture for graph classification. In Bojchevski, Aleksandar, Shchur, Oleksandr, Zügner, Daniel, & Günnemann, Stephan (2018). NetGAN: Generating graphs via random walks. In Bradshaw, John, Paige, Brooks, Kusner, Matt J., Segler, Marwin, & Hernández-Lobato, José Miguel (2019). A model to search for synthesizable molecules. In Qu, Meng, Bengio, Yoshua, & Tang, Jian (2019). GMNN: Graph Markov neural networks. In (pp. 5998–6008). Wang, Yu, Zheng, Gan, Gai, Ye (b128) 2019 Sen, Namata, Bilgic, Getoor, Galligher, Eliassi-Rad (b106) 2008; 29 Bacciu, Davide, Micheli, Alessio, & Podda, Marco (2019b). Graph generation by sequential edge prediction. In Gilbert (b47) 1959; 30 Kingma, Diederik P., & Welling, Max (2014). Auto-encoding variational Bayes. In Li, Yujia, Tarlow, Daniel, Brockschmidt, Marc, & Zemel, Richard S. (2016). Gated graph sequence neural networks. In Zhang, Zizhao, Lin, Haojie, Gao, Yue, & BNRist, KLISS (2018). Dynamic hypergraph structure learning. In Bianucci, Micheli, Sperduti, Starita (b10) 2000; 12 Cybenko (b26) 1989; 2 Neuhaus, Bunke (b94) 2005; 35 Kohonen (b73) 1990; 78 Bengio, Simard, Frasconi (b9) 1994; 5 Goodfellow, Ian, Pouget-Abadie, Jean, Mirza, Mehdi, Xu, Bing, Warde-Farley, David, & Ozair, Sherjil, et al. (2014). Generative adversarial nets. In (pp. 3734–3743). (pp. 4054–4061). Dhillon, Guan, Kulis (b30) 2007; 29 Velickovic, Petar, Cucurull, Guillem, Casanova, Arantxa, Romero, Adriana, Lio, Pietro, & Bengio, Yoshua (2018). Graph attention networks. In Blackledge (b12) 2005 Nechaev, Corcoglioniti, Giuliano (b93) 2018; 7 (pp. 2083–2092). Frasconi, Gori, Sperduti (b41) 1998; 9 (pp. 129–136). Jeon, Kim (b66) 2019; 35 Schlichtkrull, Kipf, Bloem, van den Berg, Titov, Welling (b104) 2018 Jang, Eric, Gu, Shixiang, & Poole, Ben (2017). Categorical reparametrization with gumbel-softmax. In (pp. 2508–2515). Yu, Bing, Yin, Haoteng, & Zhu, Zhanxing (2018). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In Ying, Zhitao, You, Jiaxuan, Morris, Christopher, Ren, Xiang, Hamilton, Will, & Leskovec, Jure (2018). Hierarchical graph representation learning with differentiable pooling. In Tai, Kai Sheng, Socher, Richard, & Manning, Christopher D. (2015). Improved semantic representations from tree-structured Long Short-Term Memory networks. In (pp. 3162–3169). Shchur, Mumme, Bojchevski, Günnemann (b107) 2018 Micheli (b87) 2009; 20 Samanta, Bidisha, De, Abir, Jana, Gourhari, Chattaraj, Pratim Kumar, Ganguly, Niloy, & Rodriguez, Manuel Gomez (2019). NeVAE: A deep generative model for molecular graphs. In Wu, Pan, Chen, Long, Zhang, Yu (b129) 2019 Wang, Xiaolong, & Gupta, Abhinav (2018). Videos as space-time region graphs. In Kipf, Thomas N., & Welling, Max (2017). Semi-supervised classification with graph convolutional networks. In Von Luxburg (b122) 2007; 17 Hammond, Vandergheynst, Gribonval (b59) 2011; 30 (pp. 3391–3401). Schomburg, Chang, Ebeling, Gremse, Heldt, Huhn (b105) 2004; 32 Grover, Aditya, Zweig, Aaron, & Ermon, Stefano (2019). Graphite: Iterative generative modeling of graphs. In Hagenbuchner, Sperduti, Tsoi (b52) 2003; 14 Jin, Zhang (b69) 2019 Defferrard, Michaël, Bresson, Xavier, & Vandergheynst, Pierre (2016). Convolutional neural networks on graphs with fast localized spectral filtering. In Simonovsky, Martin, & Komodakis, Nikos (2017). Dynamic edge-conditioned filters in convolutional neural networks on graphs. In (pp. 2224–2232). Battaglia, Hamrick, Bapst, Sanchez-Gonzalez, Zambaldi, Malinowski (b7) 2018 Feng, He, Tang, Chua (b37) 2019 Bacciu, Micheli, Podda (b4) 2019 Hochreiter, Schmidhuber (b62) 1997; 9 Micheli, Sona, Sperduti (b88) 2004; 15 Trentin, Rigutini (b117) 2009 Bacciu, Bruno (b1) 2020 Saul, Jordan (b102) 1999; 37 Iadarola (b63) 2018 Kipf, Welling (b71) 2016 Kwon, Yoo, Choi, Son, Lee, Kang (b74) 2019; 11 Fan, Huang (b36) 2019 Vishwanathan, Schraudolph, Kondor, Borgwardt (b121) 2010; 11 Maas, Hannun, Ng (b82) 2013 (pp. 6487–6494). Scarselli, Gori, Tsoi, Hagenbuchner, Monfardini (b103) 2009; 20 Wang, Hongwei, Wang, Jia, Wang, Jialin, Zhao, Miao, Zhang, Weinan, & Zhang, Fuzheng, et al. GraphGAN: Graph representation learning with generative adversarial nets. In Hammer, Micheli, Sperduti, Strickert (b57) 2004; 57 (pp. 5241–5250). Hochreiter (b61) 1991; 91 Bacciu, Micheli, Sperduti (b6) 2012; 23 Marcheggiani, Diego, & Titov, Ivan (2017). Encoding sentences with graph convolutional networks for semantic role labeling. In Zhou, Dengyong, Huang, Jiayuan, & Schölkopf, Bernhard (2007). Learning with hypergraphs: Clustering, classification, and embedding. In Velickovic, Petar, Fedus, William, Hamilton, William L., Liò, Pietro, Bengio, Yoshua, & Hjelm, R. Devon (2019). Deep graph infomax. In (pp. 524–532). Micheli, Sperduti, Starita (b89) 2007; 13 Borgwardt, Ong, Schönauer, Vishwanathan, Smola, Kriegel (b17) 2005; 21 Shervashidze, Schweitzer, Leeuwen, Mehlhorn, Borgwardt (b108) 2011; 12 Li, Vinyals, Dyer, Pascanu, Battaglia (b79) 2018 (pp. 1263–1272). Biggio, Roli (b11) 2018; 84 Friedman, Hastie, Tibshirani (b43) 2001 Gilmer, Justin, Schoenholz, Samuel S., Riley, Patrick F., Vinyals, Oriol, & Dahl, George E. (2017). Neural message passing for quantum chemistry. In Hamilton, Will, Ying, Zhitao, & Leskovec, Jure (2017a). Inductive representation learning on large graphs. In Beck, Daniel, Haffari, Gholamreza, & Cohn, Trevor (2018). Graph-to-sequence learning using gated graph neural networks. In (pp. 1024–1034). Sadhanala, Wang, Tibshirani (b99) 2016 Xu, Keyulu, Li, Chengtao, Tian, Yonglong, Sonobe, Tomohiro, Kawarabayash 10.1016/j.neunet.2020.06.006_b109 Yanardag (10.1016/j.neunet.2020.06.006_b132) 2015 10.1016/j.neunet.2020.06.006_b51 Wang (10.1016/j.neunet.2020.06.006_b126) 2019; 38 Bianucci (10.1016/j.neunet.2020.06.006_b10) 2000; 12 Bacciu (10.1016/j.neunet.2020.06.006_b3) 2018 10.1016/j.neunet.2020.06.006_b54 Bondy (10.1016/j.neunet.2020.06.006_b15) 1976 Hagenbuchner (10.1016/j.neunet.2020.06.006_b52) 2003; 14 Gilbert (10.1016/j.neunet.2020.06.006_b47) 1959; 30 Trentin (10.1016/j.neunet.2020.06.006_b116) 2018; 313 10.1016/j.neunet.2020.06.006_b112 Zhang (10.1016/j.neunet.2020.06.006_b144) 2019; 6 Saul (10.1016/j.neunet.2020.06.006_b102) 1999; 37 10.1016/j.neunet.2020.06.006_b110 10.1016/j.neunet.2020.06.006_b111 Wang (10.1016/j.neunet.2020.06.006_b128) 2019 10.1016/j.neunet.2020.06.006_b48 10.1016/j.neunet.2020.06.006_b49 San Kim (10.1016/j.neunet.2020.06.006_b101) 2019; 14 Biggio (10.1016/j.neunet.2020.06.006_b11) 2018; 84 Debnath (10.1016/j.neunet.2020.06.006_b28) 1991; 34 Friedman (10.1016/j.neunet.2020.06.006_b43) 2001 10.1016/j.neunet.2020.06.006_b45 Hammer (10.1016/j.neunet.2020.06.006_b57) 2004; 57 10.1016/j.neunet.2020.06.006_b46 Frasconi (10.1016/j.neunet.2020.06.006_b41) 1998; 9 10.1016/j.neunet.2020.06.006_b100 Schomburg (10.1016/j.neunet.2020.06.006_b105) 2004; 32 Hammond (10.1016/j.neunet.2020.06.006_b59) 2011; 30 Frederik Diehl (10.1016/j.neunet.2020.06.006_b42) 2019 Gallicchio (10.1016/j.neunet.2020.06.006_b44) 2010 Hochreiter (10.1016/j.neunet.2020.06.006_b61) 1991; 91 Zitnik (10.1016/j.neunet.2020.06.006_b146) 2018; 34 10.1016/j.neunet.2020.06.006_b76 Sadhanala (10.1016/j.neunet.2020.06.006_b99) 2016 10.1016/j.neunet.2020.06.006_b77 Vishwanathan (10.1016/j.neunet.2020.06.006_b121) 2010; 11 10.1016/j.neunet.2020.06.006_b78 Frasconi (10.1016/j.neunet.2020.06.006_b40) 2014; 217 Hamilton (10.1016/j.neunet.2020.06.006_b55) 2017; 40 10.1016/j.neunet.2020.06.006_b70 Bengio (10.1016/j.neunet.2020.06.006_b9) 1994; 5 Cortes (10.1016/j.neunet.2020.06.006_b25) 1995; 20 10.1016/j.neunet.2020.06.006_b72 Ribeiro (10.1016/j.neunet.2020.06.006_b98) 2017 Hammer (10.1016/j.neunet.2020.06.006_b56) 2005; 17 De Cao (10.1016/j.neunet.2020.06.006_b27) 2018 Lovász (10.1016/j.neunet.2020.06.006_b81) 1993; 2 Micheli (10.1016/j.neunet.2020.06.006_b88) 2004; 15 Cybenko (10.1016/j.neunet.2020.06.006_b26) 1989; 2 Von Luxburg (10.1016/j.neunet.2020.06.006_b122) 2007; 17 Ralaivola (10.1016/j.neunet.2020.06.006_b97) 2005; 18 Bongini (10.1016/j.neunet.2020.06.006_b16) 2018; 29 LeCun (10.1016/j.neunet.2020.06.006_b75) 1995; 3361 Grover (10.1016/j.neunet.2020.06.006_b50) 2016 10.1016/j.neunet.2020.06.006_b64 10.1016/j.neunet.2020.06.006_b65 Borgwardt (10.1016/j.neunet.2020.06.006_b17) 2005; 21 Dhillon (10.1016/j.neunet.2020.06.006_b30) 2007; 29 10.1016/j.neunet.2020.06.006_b67 10.1016/j.neunet.2020.06.006_b68 Sperduti (10.1016/j.neunet.2020.06.006_b113) 1997; 8 Bacciu (10.1016/j.neunet.2020.06.006_b6) 2012; 23 Chapelle (10.1016/j.neunet.2020.06.006_b22) 2006; 20 Erdős (10.1016/j.neunet.2020.06.006_b33) 1960; 5 Sen (10.1016/j.neunet.2020.06.006_b106) 2008; 29 Kohonen (10.1016/j.neunet.2020.06.006_b73) 1990; 78 Hochreiter (10.1016/j.neunet.2020.06.006_b62) 1997; 9 10.1016/j.neunet.2020.06.006_b18 Hammer (10.1016/j.neunet.2020.06.006_b58) 2004; 17 10.1016/j.neunet.2020.06.006_b96 Kipf (10.1016/j.neunet.2020.06.006_b71) 2016 10.1016/j.neunet.2020.06.006_b14 Massarelli (10.1016/j.neunet.2020.06.006_b86) 2019 Nechaev (10.1016/j.neunet.2020.06.006_b93) 2018; 7 10.1016/j.neunet.2020.06.006_b90 Dobson (10.1016/j.neunet.2020.06.006_b31) 2003; 330 10.1016/j.neunet.2020.06.006_b91 Fey (10.1016/j.neunet.2020.06.006_b39) 2019 10.1016/j.neunet.2020.06.006_b92 Perozzi (10.1016/j.neunet.2020.06.006_b95) 2014 Jeon (10.1016/j.neunet.2020.06.006_b66) 2019; 35 Bacciu (10.1016/j.neunet.2020.06.006_b4) 2019 Yin (10.1016/j.neunet.2020.06.006_b134) 2019; 185 10.1016/j.neunet.2020.06.006_b138 Kwon (10.1016/j.neunet.2020.06.006_b74) 2019; 11 10.1016/j.neunet.2020.06.006_b139 10.1016/j.neunet.2020.06.006_b136 10.1016/j.neunet.2020.06.006_b137 Feng (10.1016/j.neunet.2020.06.006_b37) 2019 10.1016/j.neunet.2020.06.006_b84 10.1016/j.neunet.2020.06.006_b85 Trentin (10.1016/j.neunet.2020.06.006_b117) 2009 Bacciu (10.1016/j.neunet.2020.06.006_b1) 2020 Macskassy (10.1016/j.neunet.2020.06.006_b83) 2007; 8 Blackledge (10.1016/j.neunet.2020.06.006_b12) 2005 10.1016/j.neunet.2020.06.006_b80 Shchur (10.1016/j.neunet.2020.06.006_b107) 2018 10.1016/j.neunet.2020.06.006_b145 10.1016/j.neunet.2020.06.006_b143 Bronstein (10.1016/j.neunet.2020.06.006_b19) 2017; 34 10.1016/j.neunet.2020.06.006_b141 Wu (10.1016/j.neunet.2020.06.006_b129) 2019 Li (10.1016/j.neunet.2020.06.006_b79) 2018 Maas (10.1016/j.neunet.2020.06.006_b82) 2013 10.1016/j.neunet.2020.06.006_b38 Zambon (10.1016/j.neunet.2020.06.006_b140) 2018; 29 Jin (10.1016/j.neunet.2020.06.006_b69) 2019 10.1016/j.neunet.2020.06.006_b127 10.1016/j.neunet.2020.06.006_b125 Bobadilla (10.1016/j.neunet.2020.06.006_b13) 2013; 46 Hagenbuchner (10.1016/j.neunet.2020.06.006_b53) 2009; 72 10.1016/j.neunet.2020.06.006_b32 Ying (10.1016/j.neunet.2020.06.006_b135) 2018 10.1016/j.neunet.2020.06.006_b34 10.1016/j.neunet.2020.06.006_b35 Schlichtkrull (10.1016/j.neunet.2020.06.006_b104) 2018 Bacciu (10.1016/j.neunet.2020.06.006_b2) 2019 Micheli (10.1016/j.neunet.2020.06.006_b87) 2009; 20 10.1016/j.neunet.2020.06.006_b133 10.1016/j.neunet.2020.06.006_b130 10.1016/j.neunet.2020.06.006_b131 Scarselli (10.1016/j.neunet.2020.06.006_b103) 2009; 20 Wale (10.1016/j.neunet.2020.06.006_b124) 2008; 14 10.1016/j.neunet.2020.06.006_b118 10.1016/j.neunet.2020.06.006_b29 10.1016/j.neunet.2020.06.006_b119 Zhang (10.1016/j.neunet.2020.06.006_b142) 2018 Iadarola (10.1016/j.neunet.2020.06.006_b63) 2018 10.1016/j.neunet.2020.06.006_b114 10.1016/j.neunet.2020.06.006_b115 Battaglia (10.1016/j.neunet.2020.06.006_b7) 2018 10.1016/j.neunet.2020.06.006_b20 10.1016/j.neunet.2020.06.006_b21 Fan (10.1016/j.neunet.2020.06.006_b36) 2019 10.1016/j.neunet.2020.06.006_b23 10.1016/j.neunet.2020.06.006_b24 10.1016/j.neunet.2020.06.006_b5 Shervashidze (10.1016/j.neunet.2020.06.006_b108) 2011; 12 Helma (10.1016/j.neunet.2020.06.006_b60) 2001; 17 Micheli (10.1016/j.neunet.2020.06.006_b89) 2007; 13 10.1016/j.neunet.2020.06.006_b8 Neuhaus (10.1016/j.neunet.2020.06.006_b94) 2005; 35 10.1016/j.neunet.2020.06.006_b123 Zügner (10.1016/j.neunet.2020.06.006_b147) 2018 10.1016/j.neunet.2020.06.006_b120 |
| References_xml | – volume: 57 start-page: 3 year: 2004 end-page: 35 ident: b57 article-title: A general framework for unsupervised processing of structured data publication-title: Neurocomputing – volume: 14 year: 2019 ident: b101 article-title: Graph convolutional network approach applied to predict hourly bike-sharing demands considering spatial, temporal, and global effects publication-title: PloS One – reference: Calandriello, Daniele, Koutis, Ioannis, Lazaric, Alessandro, & Valko, Michal (2018). Improved large-scale graph learning through ridge spectral sparsification. In – start-page: 701 year: 2014 end-page: 710 ident: b95 article-title: Deepwalk: Online learning of social representations publication-title: Proceedings of the 20th international conference on knowledge discovery and data mining (SIGKDD) – reference: (pp. 6487–6494). – reference: Cho, Kyunghyun, van Merrienboer, Bart, Gülçehre, Çaglar, Bahdanau, Dzmitry, Bougares, Fethi, & Schwenk, Holger, et al. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In – reference: Marcheggiani, Diego, Bastings, Joost, & Titov, Ivan (2018). Exploiting semantics in neural machine translation with graph convolutional networks. In – reference: Xu, Keyulu, Hu, Weihua, Leskovec, Jure, & Jegelka, Stefanie (2019). How powerful are graph neural networks? In – volume: 30 start-page: 1141 year: 1959 end-page: 1144 ident: b47 article-title: Random graphs publication-title: The Annals of Mathematical Statistics – volume: 2 start-page: 1 year: 1993 end-page: 46 ident: b81 article-title: Random walks on graphs: A survey publication-title: Combinatorics, Paul Erdos is Eighty – reference: (pp. 486–492). – reference: (pp. 7935–7947). – year: 2001 ident: b43 article-title: The elements of statistical learning, Vol. 1 – reference: Jang, Eric, Gu, Shixiang, & Poole, Ben (2017). Categorical reparametrization with gumbel-softmax. In – year: 2019 ident: b129 article-title: A comprehensive survey on graph neural networks – reference: Fahlman, Scott E., & Lebiere, Christian (1990). The Cascade-Correlation learning architecture. In – start-page: 294 year: 2019 end-page: 306 ident: b2 article-title: A non-negative factorization approach to node pooling in graph convolutional neural networks publication-title: AI*IA 2019 – Advances in artificial intelligence – volume: 20 start-page: 542 year: 2006 ident: b22 article-title: Semi-supervised learning publication-title: IEEE Transactions on Neural Networks – reference: (pp. 524–532). – reference: Jiang, Jianwen, Wei, Yuxuan, Feng, Yifan, Cao, Jingxuan, & Gao, Yue (2019). Dynamic hypergraph neural networks. In – reference: Zaheer, Manzil, Kottur, Satwik, Ravanbakhsh, Siamak, Poczos, Barnabas, Salakhutdinov, Ruslan R., & Smola, Alexander J. (2017). Deep sets. In – volume: 21 start-page: i47 year: 2005 end-page: i56 ident: b17 article-title: Protein function prediction via graph kernels publication-title: Bioinformatics – reference: Marcheggiani, Diego, & Titov, Ivan (2017). Encoding sentences with graph convolutional networks for semantic role labeling. In – reference: Simonovsky, Martin, & Komodakis, Nikos GraphVAE: Towards generation of small graphs using variational autoencoders. In – volume: 2 start-page: 303 year: 1989 end-page: 314 ident: b26 article-title: Approximation by superpositions of a sigmoidal function publication-title: Mathematics of Control, Signals and Systems – year: 2018 ident: b27 article-title: MolGAN: An implicit generative model for small molecular graphs publication-title: Workshop on theoretical foundations and applications of deep generative models, international conference on machine learning (ICML) – year: 1976 ident: b15 article-title: Graph theory with applications, Vol. 290 – reference: Bruna, Joan, Zaremba, Wojciech, Szlam, Arthur, & LeCun, Yann (2014). Spectral networks and locally connected networks on graphs. In – year: 2019 ident: b42 article-title: Towards graph pooling by edge contraction publication-title: Workshop on learning and reasoning with graph-structured data, international conference on machine learning (ICML) – year: 2018 ident: b79 article-title: Learning deep generative models of graphs – reference: Jin, Wengong, Barzilay, Regina, & Jaakkola, Tommi S. (2018). Junction tree variational autoencoder for molecular graph generation. In – reference: (pp. 1601–1608). – start-page: 974 year: 2018 end-page: 983 ident: b135 article-title: Graph convolutional neural networks for web-scale recommender systems publication-title: Proceedings of the 24th international conference on knowledge discovery and data mining (SIGKDD) – reference: Li, Yujia, Tarlow, Daniel, Brockschmidt, Marc, & Zemel, Richard S. (2016). Gated graph sequence neural networks. In – reference: Shervashidze, Nino, Vishwanathan, SVN, Petri, Tobias, Mehlhorn, Kurt, & Borgwardt, Karsten (2009). Efficient graphlet kernels for large graph comparison. In – reference: (pp. 609–618). – reference: (pp. 2224–2232). – reference: (pp. 399–417). – reference: (pp. 1724–1734). – reference: Hamilton, Will, Ying, Zhitao, & Leskovec, Jure (2017a). Inductive representation learning on large graphs. In – reference: Li, Qimai, Han, Zhichao, & Wu, Xiao-Ming (2018). Deeper insights into graph convolutional networks for semi-supervised learning. In – volume: 34 start-page: i457 year: 2018 end-page: i466 ident: b146 article-title: Modeling polypharmacy side effects with graph convolutional networks publication-title: Bioinformatics – volume: 14 start-page: 491 year: 2003 end-page: 505 ident: b52 article-title: A self-organizing map for adaptive processing of structured data publication-title: IEEE Transactions on Neural Networks – volume: 46 start-page: 109 year: 2013 end-page: 132 ident: b13 article-title: Recommender systems survey publication-title: Knowledge-Based Systems – reference: (pp. 4054–4061). – start-page: 40 year: 2009 end-page: 49 ident: b117 article-title: A maximum-likelihood connectionist model for unsupervised learning over graphical domains publication-title: Proceedings of the 12th international conference on artificial neural networks (ICANN) – volume: 5 start-page: 17 year: 1960 end-page: 60 ident: b33 article-title: On the evolution of random graphs publication-title: Publications of the Mathematical Institute of the Hungarian Academy of Science – volume: 8 start-page: 714 year: 1997 end-page: 735 ident: b113 article-title: Supervised neural networks for the classification of structures publication-title: IEEE Transactions on Neural Networks – reference: Samanta, Bidisha, De, Abir, Jana, Gourhari, Chattaraj, Pratim Kumar, Ganguly, Niloy, & Rodriguez, Manuel Gomez (2019). NeVAE: A deep generative model for molecular graphs. In – reference: (pp. 2328–2337). – reference: Beck, Daniel, Haffari, Gholamreza, & Cohn, Trevor (2018). Graph-to-sequence learning using gated graph neural networks. In – reference: Ying, Zhitao, You, Jiaxuan, Morris, Christopher, Ren, Xiang, Hamilton, Will, & Leskovec, Jure (2018). Hierarchical graph representation learning with differentiable pooling. In – volume: 17 start-page: 107 year: 2001 end-page: 108 ident: b60 article-title: The predictive toxicology challenge 2000–2001 publication-title: Bioinformatics – volume: 18 start-page: 1093 year: 2005 end-page: 1110 ident: b97 article-title: Graph kernels for chemical informatics publication-title: Neural Networks – year: 2019 ident: b39 article-title: Fast graph representation learning with PyTorch Geometric publication-title: Workshop on representation learning on graphs and manifolds, international conference on learning representations (ICLR) – reference: Namata, Galileo Mark, London, Ben, Getoor, Lise, & Huang, Bert (2012). Query-driven active surveying for collective classification. In – volume: 91 year: 1991 ident: b61 article-title: Untersuchungen zu dynamischen neuronalen netzen publication-title: Diploma, Technische Universität München – volume: 330 start-page: 771 year: 2003 end-page: 783 ident: b31 article-title: Distinguishing enzyme structures from non-enzymes without alignments publication-title: Journal of Molecular Biology – reference: (pp. 3844–3852). – reference: Tolstikhin, Ilya, Bousquet, Olivier, Gelly, Sylvain, & Schoelkopf, Bernhard (2018). Wasserstein auto-encoders. In – volume: 72 start-page: 1419 year: 2009 end-page: 1430 ident: b53 article-title: Graph self-organizing maps for cyclic and unbounded graphs publication-title: Neurocomputing – reference: Liu, Qi, Allamanis, Miltiadis, Brockschmidt, Marc, & Gaunt, Alexander (2018). Constrained graph variational autoencoders for molecule design. In – reference: Zhang, Zizhao, Lin, Haojie, Gao, Yue, & BNRist, KLISS (2018). Dynamic hypergraph structure learning. In – reference: Feng, Yifan, You, Haoxuan, Zhang, Zizhao, Ji, Rongrong, & Gao, Yue (2019). Hypergraph neural networks. In – volume: 17 start-page: 1061 year: 2004 end-page: 1085 ident: b58 article-title: Recursive self-organizing network models publication-title: Neural Networks – volume: 217 start-page: 117 year: 2014 end-page: 143 ident: b40 article-title: Klog: A language for logical and relational learning with kernels publication-title: Artificial Intelligence – volume: 35 start-page: 503 year: 2005 end-page: 514 ident: b94 article-title: Self-organizing maps for learning the edit costs in graph matching publication-title: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) – volume: 34 start-page: 25 year: 2017 ident: b19 article-title: Geometric deep learning: going beyond Euclidean data publication-title: IEEE Signal Processing Magazine – start-page: 1 year: 2010 end-page: 8 ident: b44 article-title: Graph echo state networks publication-title: Proceedings of the international joint conference on neural networks (IJCNN) – volume: 9 start-page: 768 year: 1998 end-page: 786 ident: b41 article-title: A general framework for adaptive processing of data structures publication-title: IEEE Transactions on Neural Networks – reference: Zhang, Muhan, Cui, Zhicheng, Neumann, Marion, & Chen, Yixin (2018). An end-to-end deep learning architecture for graph classification. In – volume: 29 start-page: 1944 year: 2007 end-page: 1957 ident: b30 article-title: Weighted graph cuts without eigenvectors a multilevel approach publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – reference: Duvenaud, David K., Maclaurin, Dougal, Iparraguirre, Jorge, Bombarelli, Rafael, Hirzel, Timothy, & Aspuru-Guzik, Alan, et al. (2015). Convolutional networks on graphs for learning molecular fingerprints. In – reference: Velickovic, Petar, Cucurull, Guillem, Casanova, Arantxa, Romero, Adriana, Lio, Pietro, & Bengio, Yoshua (2018). Graph attention networks. In – reference: (pp. 2191–2200). – volume: 11 start-page: 1201 year: 2010 end-page: 1242 ident: b121 article-title: Graph kernels publication-title: Journal of Machine Learning Research (JMLR) – reference: (pp. 3558–3565). – start-page: 1365 year: 2015 end-page: 1374 ident: b132 article-title: Deep graph kernels publication-title: Proceedings of the 21th international conference on knowledge discovery and data mining (SIGKDD – start-page: 1250 year: 2016 end-page: 1259 ident: b99 article-title: Graph sparsification approaches for laplacian smoothing publication-title: Artificial intelligence and statistics – start-page: 30 year: 2005 end-page: 49 ident: b12 article-title: Chapter 2 - 2d fourier theory publication-title: Digital image processing – year: 2018 ident: b107 article-title: Pitfalls of graph neural network evaluation publication-title: Workshop on relational representation learning, neural information processing systems (NeurIPS) – year: 2019 ident: b37 article-title: Graph adversarial training: Dynamically regularizing based on graph structure publication-title: IEEE Transactions on Knowledge and Data Engineering – reference: Vaswani, Ashish, Shazeer, Noam, Parmar, Niki, Uszkoreit, Jakob, Jones, Llion, & Gomez, Aidan N., et al. (2017). Attention is all you need. In – reference: (pp. 273–283). – reference: Gallicchio, Claudio, & Micheli, Alessio (2020). Fast and deep graph neural networks. In – reference: Gilmer, Justin, Schoenholz, Samuel S., Riley, Patrick F., Vinyals, Oriol, & Dahl, George E. (2017). Neural message passing for quantum chemistry. In – reference: (pp. 687–696). – volume: 11 start-page: 70 year: 2019 ident: b74 article-title: Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation publication-title: Journal of Cheminformatics – reference: Mishra, Pushkar, Yannakoudakis, Helen, & Shutova, Ekaterina (2018). Neural character-based composition models for abuse detection. In – reference: (pp. 412–422). – reference: (pp. 3391–3401). – reference: (pp. 2508–2515). – volume: 29 start-page: 5441 year: 2018 end-page: 5458 ident: b16 article-title: Recursive neural networks for density estimation over generalized random graphs publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: Tai, Kai Sheng, Socher, Richard, & Manning, Christopher D. (2015). Improved semantic representations from tree-structured Long Short-Term Memory networks. In – reference: Simonovsky, Martin, & Komodakis, Nikos (2017). Dynamic edge-conditioned filters in convolutional neural networks on graphs. In – start-page: 309 year: 2019 end-page: 329 ident: b86 article-title: Safe: Self-attentive function embeddings for binary similarity publication-title: Proceedings of the 16th international conference on detection of intrusions and malware, and vulnerability assessment (DIMVA) – reference: (pp. 1263–1272). – year: 2013 ident: b82 article-title: Rectifier nonlinearities improve neural network acoustic models publication-title: Workshop on deep learning for audio, speech and language processing, international conference on machine learning (ICML) – start-page: 385 year: 2017 end-page: 394 ident: b98 article-title: Struc2vec: Learning node representations from structural identity publication-title: Proceedings of the 23rd international conference on knowledge discovery and data mining (SIGKDD) – reference: Grover, Aditya, Zweig, Aaron, & Ermon, Stefano (2019). Graphite: Iterative generative modeling of graphs. In – volume: 78 start-page: 1464 year: 1990 end-page: 1480 ident: b73 article-title: The self-organizing map publication-title: Proceedings of the IEEE – reference: (pp. 2434–2444). – reference: Bacciu, Davide, Micheli, Alessio, & Podda, Marco (2019b). Graph generation by sequential edge prediction. In – volume: 23 start-page: 1987 year: 2012 end-page: 2002 ident: b6 article-title: Compositional generative mapping for tree-structured data - part I: Bottom-up probabilistic modeling of trees publication-title: IEEE Transactions on Neural Networks and Learning Systems – year: 2019 ident: b128 article-title: Deep graph library: Towards efficient and scalable deep learning on graphs publication-title: Workshop on representation learning on graphs and manifolds, international conference on learning representations (ICLR) – start-page: 294 year: 2018 end-page: 303 ident: b3 article-title: Contextual graph Markov model: A deep and generative approach to graph processing publication-title: Proceedings of the 35th international conference on machine learning (ICML), Vol. 80 – volume: 13 start-page: 1469 year: 2007 end-page: 1496 ident: b89 article-title: An introduction to recursive neural networks and kernel methods for cheminformatics publication-title: Current Pharmaceutical Design – volume: 40 start-page: 52 year: 2017 end-page: 74 ident: b55 article-title: Representation learning on graphs: Methods and applications publication-title: IEEE Data Engineering Bulletin – volume: 14 start-page: 347 year: 2008 end-page: 375 ident: b124 article-title: Comparison of descriptor spaces for chemical compound retrieval and classification publication-title: Knowledge and Information Systems – start-page: 855 year: 2016 end-page: 864 ident: b50 article-title: Node2vec: Scalable feature learning for networks publication-title: Proceedings of the 22nd international conference on knowledge discovery and data mining (SIGKDD) – volume: 17 start-page: 1109 year: 2005 end-page: 1159 ident: b56 article-title: Universal approximation capability of cascade correlation for structures publication-title: Neural Computation – reference: (pp. 3162–3169). – reference: Wagstaff, Edward, Fuchs, Fabian B., Engelcke, Martin, Posner, Ingmar, & Osborne, Michael (2019). On the limitations of representing functions on sets. In – start-page: 236 year: 2020 end-page: 245 ident: b1 article-title: Deep tree transductions - a short survey publication-title: Recent advances in big data and deep learning – start-page: 2847 year: 2018 end-page: 2856 ident: b147 article-title: Adversarial attacks on neural networks for graph data publication-title: Proceedings of the 24th international conference on knowledge discovery and data mining (SIGKDD) – reference: Errica, Federico, Podda, Marco, Bacciu, Davide, & Micheli, Alessio (2020). A fair comparison of graph neural networks for graph classification. In – reference: Yu, Bing, Yin, Haoteng, & Zhu, Zhanxing (2018). Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In – reference: Wang, Xiaolong, & Gupta, Abhinav (2018). Videos as space-time region graphs. In – volume: 34 start-page: 786 year: 1991 end-page: 797 ident: b28 article-title: Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds correlation with molecular orbital energies and hydrophobicity publication-title: Journal of Medicinal Chemistry – reference: (pp. 2083–2092). – reference: Bradshaw, John, Paige, Brooks, Kusner, Matt J., Segler, Marwin, & Hernández-Lobato, José Miguel (2019). A model to search for synthesizable molecules. In – volume: 12 start-page: 117 year: 2000 end-page: 147 ident: b10 article-title: Application of cascade correlation networks for structures to chemistry publication-title: Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies – reference: Chen, Jie, Ma, Tengfei, & Xiao, Cao (2018). FastGCN: Fast learning with graph convolutional networks via importance sampling. In – reference: Goodfellow, Ian, Pouget-Abadie, Jean, Mirza, Mehdi, Xu, Bing, Warde-Farley, David, & Ozair, Sherjil, et al. (2014). Generative adversarial nets. In – reference: (pp. 7795–7804). – volume: 15 start-page: 1396 year: 2004 end-page: 1410 ident: b88 article-title: Contextual processing of structured data by recursive cascade correlation publication-title: IEEE Transactions on Neural Networks – volume: 84 start-page: 317 year: 2018 end-page: 331 ident: b11 article-title: Wild patterns: Ten years after the rise of adversarial machine learning publication-title: Pattern Recognition – volume: 30 start-page: 129 year: 2011 end-page: 150 ident: b59 article-title: Wavelets on graphs via spectral graph theory publication-title: Applied and Computational Harmonic Analysis – reference: (pp. 1–10). – volume: 20 start-page: 61 year: 2009 end-page: 80 ident: b103 article-title: The graph neural network model publication-title: IEEE Transactions on Neural Networks – reference: You, Jiaxuan, Ying, Rex, Ren, Xiang, Hamilton, William L., & Leskovec, Jure (2018). GraphRNN: Generating realistic graphs with deep auto-regressive models. In – volume: 6 start-page: 11 year: 2019 ident: b144 article-title: Graph convolutional networks: a comprehensive review publication-title: Computational Social Networks – reference: Velickovic, Petar, Fedus, William, Hamilton, William L., Liò, Pietro, Bengio, Yoshua, & Hjelm, R. Devon (2019). Deep graph infomax. In – reference: (pp. 2672–2680). – reference: (pp. 1024–1034). – volume: 8 start-page: 935 year: 2007 end-page: 983 ident: b83 article-title: Classification in networked data: A toolkit and a univariate case study publication-title: Journal of Machine Learning Research (JMLR) – reference: Monti, Federico, Bronstein, Michael M., & Bresson, Xavier (2017). Geometric matrix completion with recurrent multi-graph neural networks. In – reference: (pp. 5453–5462). – reference: Ivanov, Sergey, & Burnaev, Evgeny (2018). Anonymous walk embeddings. In – reference: Lee, Junhyun, Lee, Inyeop, & Kang, Jaewoo (2019). Self-attention graph pooling. In – reference: Yang, Liang, Kang, Zesheng, Cao, Xiaochun, Jin, Di, Yang, Bo, & Guo, Yuanfang Topology optimization based graph convolutional network. In – volume: 5 start-page: 157 year: 1994 end-page: 166 ident: b9 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Transactions on Neural Networks – volume: 185 start-page: 105020 year: 2019 ident: b134 article-title: A deeper graph neural network for recommender systems publication-title: Knowledge-Based Systems – volume: 32 year: 2004 ident: b105 article-title: BRENDA, the enzyme database: updates and major new developments publication-title: Nucleic Acids Research – reference: (pp. 129–136). – year: 2019 ident: b4 article-title: Edge-based sequential graph generation with recurrent neural networks publication-title: Neurocomputing – reference: Kipf, Thomas N., & Welling, Max (2017). Semi-supervised classification with graph convolutional networks. In – volume: 29 start-page: 5592 year: 2018 end-page: 5605 ident: b140 article-title: Concept drift and anomaly detection in graph streams publication-title: IEEE Transactions on Neural Networks and Learning Systems – reference: (pp. 3734–3743). – volume: 20 start-page: 498 year: 2009 end-page: 511 ident: b87 article-title: Neural network for graphs: A contextual constructive approach publication-title: IEEE Transactions on Neural Networks – reference: Xu, Keyulu, Li, Chengtao, Tian, Yonglong, Sonobe, Tomohiro, Kawarabayashi, Ken-ichi, & Jegelka, Stefanie (2018). Representation learning on graphs with jumping knowledge networks. In – year: 2019 ident: b36 article-title: Conditional labeled graph generation with GANs publication-title: Workshop on representation learning on graphs and manifolds, international conference on learning representations (ICLR) – year: 2018 ident: b63 article-title: Graph-based classification for detecting instances of bug patterns – year: 2019 ident: b69 article-title: Latent adversarial training of graph convolution networks publication-title: Workshop on learning and reasoning with graph-structured representations, international conference on machine learning (ICML) – reference: (pp. 1110–1117). – volume: 37 start-page: 75 year: 1999 end-page: 87 ident: b102 article-title: Mixed memory Markov models: Decomposing complex stochastic processes as mixtures of simpler ones publication-title: Machine Learning – reference: Zhou, Dengyong, Huang, Jiayuan, & Schölkopf, Bernhard (2007). Learning with hypergraphs: Clustering, classification, and embedding. In – reference: Gao, Hongyang, & Ji, Shuiwang (2019). Graph U-nets. In – volume: 35 start-page: 4979 year: 2019 end-page: 4985 ident: b66 article-title: FP2VEC: A new molecular featurizer for learning molecular properties publication-title: Bioinformatics – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: b62 article-title: Long short-term memory publication-title: Neural Computation – start-page: 593 year: 2018 end-page: 607 ident: b104 article-title: Modeling relational data with graph convolutional networks publication-title: Proceedings of the 15th european semantic web conference (ESWC) – volume: 29 start-page: 93 year: 2008 ident: b106 article-title: Collective classification in network data publication-title: AI Magazine – reference: (pp. 2635–2641). – volume: 7 start-page: 251 year: 2018 end-page: 272 ident: b93 article-title: Sociallink: exploiting graph embeddings to link DBpedia entities to Twitter profiles publication-title: Progress in Artificial Intelligence – volume: 12 start-page: 2539 year: 2011 end-page: 2561 ident: b108 article-title: Weisfeiler-lehman graph kernels publication-title: Journal of Machine Learning Research (JMLR) – reference: (pp. 3693–3702). – reference: Defferrard, Michaël, Bresson, Xavier, & Vandergheynst, Pierre (2016). Convolutional neural networks on graphs with fast localized spectral filtering. In – volume: 38 start-page: 146 year: 2019 ident: b126 article-title: Dynamic graph cnn for learning on point clouds publication-title: ACM Transactions on Graphics – year: 2018 ident: b142 article-title: Deep learning on graphs: A survey – reference: (pp. 488–495). – volume: 313 start-page: 14 year: 2018 end-page: 24 ident: b116 article-title: Nonparametric small random networks for graph-structured pattern recognition publication-title: Neurocomputing – volume: 3361 start-page: 1995 year: 1995 ident: b75 article-title: Convolutional networks for images, speech, and time series publication-title: The Handbook of Brain Theory and Neural Networks – reference: Qu, Meng, Bengio, Yoshua, & Tang, Jian (2019). GMNN: Graph Markov neural networks. In – reference: (pp. 1556–1566). – reference: . – year: 2018 ident: b7 article-title: Relational inductive biases, deep learning, and graph networks – reference: Kingma, Diederik P., & Welling, Max (2014). Auto-encoding variational Bayes. In – reference: (pp. 1506–1515). – reference: (pp. 3700–3710). – reference: Wang, Hongwei, Wang, Jia, Wang, Jialin, Zhao, Miao, Zhang, Weinan, & Zhang, Fuzheng, et al. GraphGAN: Graph representation learning with generative adversarial nets. In – reference: Socher, Richard, Lin, Cliff C., Manning, Chris, & Ng, Andrew Y. (2011). Parsing natural scenes and natural language with recursive neural networks. In – reference: (pp. 5998–6008). – year: 2016 ident: b71 article-title: Variational graph auto-encoders publication-title: Workshop on Bayesian deep learning, neural information processing system (NIPS) – reference: (pp. 5241–5250). – reference: Bojchevski, Aleksandar, Shchur, Oleksandr, Zügner, Daniel, & Günnemann, Stephan (2018). NetGAN: Generating graphs via random walks. In – volume: 17 start-page: 395 year: 2007 end-page: 416 ident: b122 article-title: A tutorial on spectral clustering publication-title: Statistics and Computing – volume: 20 start-page: 273 year: 1995 end-page: 297 ident: b25 article-title: Support-vector networks publication-title: Machine Learning – volume: 7 start-page: 251 issue: 4 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b93 article-title: Sociallink: exploiting graph embeddings to link DBpedia entities to Twitter profiles publication-title: Progress in Artificial Intelligence doi: 10.1007/s13748-018-0160-x – volume: 57 start-page: 3 year: 2004 ident: 10.1016/j.neunet.2020.06.006_b57 article-title: A general framework for unsupervised processing of structured data publication-title: Neurocomputing doi: 10.1016/j.neucom.2004.01.008 – volume: 17 start-page: 107 issue: 1 year: 2001 ident: 10.1016/j.neunet.2020.06.006_b60 article-title: The predictive toxicology challenge 2000–2001 publication-title: Bioinformatics doi: 10.1093/bioinformatics/17.1.107 – year: 2018 ident: 10.1016/j.neunet.2020.06.006_b79 – ident: 10.1016/j.neunet.2020.06.006_b138 doi: 10.24963/ijcai.2018/505 – volume: 30 start-page: 129 issue: 2 year: 2011 ident: 10.1016/j.neunet.2020.06.006_b59 article-title: Wavelets on graphs via spectral graph theory publication-title: Applied and Computational Harmonic Analysis doi: 10.1016/j.acha.2010.04.005 – ident: 10.1016/j.neunet.2020.06.006_b139 – volume: 9 start-page: 768 issue: 5 year: 1998 ident: 10.1016/j.neunet.2020.06.006_b41 article-title: A general framework for adaptive processing of data structures publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.712151 – volume: 14 start-page: 347 issue: 3 year: 2008 ident: 10.1016/j.neunet.2020.06.006_b124 article-title: Comparison of descriptor spaces for chemical compound retrieval and classification publication-title: Knowledge and Information Systems doi: 10.1007/s10115-007-0103-5 – ident: 10.1016/j.neunet.2020.06.006_b131 – ident: 10.1016/j.neunet.2020.06.006_b68 – ident: 10.1016/j.neunet.2020.06.006_b24 doi: 10.3115/v1/D14-1179 – volume: 30 start-page: 1141 issue: 4 year: 1959 ident: 10.1016/j.neunet.2020.06.006_b47 article-title: Random graphs publication-title: The Annals of Mathematical Statistics doi: 10.1214/aoms/1177706098 – ident: 10.1016/j.neunet.2020.06.006_b54 – ident: 10.1016/j.neunet.2020.06.006_b80 – ident: 10.1016/j.neunet.2020.06.006_b133 doi: 10.24963/ijcai.2019/563 – start-page: 30 year: 2005 ident: 10.1016/j.neunet.2020.06.006_b12 article-title: Chapter 2 - 2d fourier theory – ident: 10.1016/j.neunet.2020.06.006_b77 doi: 10.1609/aaai.v32i1.11604 – start-page: 40 year: 2009 ident: 10.1016/j.neunet.2020.06.006_b117 article-title: A maximum-likelihood connectionist model for unsupervised learning over graphical domains – year: 2018 ident: 10.1016/j.neunet.2020.06.006_b142 – volume: 9 start-page: 1735 issue: 8 year: 1997 ident: 10.1016/j.neunet.2020.06.006_b62 article-title: Long short-term memory publication-title: Neural Computation doi: 10.1162/neco.1997.9.8.1735 – year: 2001 ident: 10.1016/j.neunet.2020.06.006_b43 – volume: 14 start-page: 491 issue: 3 year: 2003 ident: 10.1016/j.neunet.2020.06.006_b52 article-title: A self-organizing map for adaptive processing of structured data publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2003.810735 – ident: 10.1016/j.neunet.2020.06.006_b92 – year: 2018 ident: 10.1016/j.neunet.2020.06.006_b27 article-title: MolGAN: An implicit generative model for small molecular graphs – ident: 10.1016/j.neunet.2020.06.006_b141 doi: 10.1609/aaai.v32i1.11782 – volume: 40 start-page: 52 issue: 3 year: 2017 ident: 10.1016/j.neunet.2020.06.006_b55 article-title: Representation learning on graphs: Methods and applications publication-title: IEEE Data Engineering Bulletin – volume: 8 start-page: 935 issue: May year: 2007 ident: 10.1016/j.neunet.2020.06.006_b83 article-title: Classification in networked data: A toolkit and a univariate case study publication-title: Journal of Machine Learning Research (JMLR) – year: 2013 ident: 10.1016/j.neunet.2020.06.006_b82 article-title: Rectifier nonlinearities improve neural network acoustic models – volume: 14 issue: 9 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b101 article-title: Graph convolutional network approach applied to predict hourly bike-sharing demands considering spatial, temporal, and global effects publication-title: PloS One – start-page: 236 year: 2020 ident: 10.1016/j.neunet.2020.06.006_b1 article-title: Deep tree transductions - a short survey – ident: 10.1016/j.neunet.2020.06.006_b120 – volume: 11 start-page: 70 issue: 1 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b74 article-title: Efficient learning of non-autoregressive graph variational autoencoders for molecular graph generation publication-title: Journal of Cheminformatics doi: 10.1186/s13321-019-0396-x – year: 2018 ident: 10.1016/j.neunet.2020.06.006_b63 – year: 2018 ident: 10.1016/j.neunet.2020.06.006_b107 article-title: Pitfalls of graph neural network evaluation – volume: 17 start-page: 1061 issue: 8–9 year: 2004 ident: 10.1016/j.neunet.2020.06.006_b58 article-title: Recursive self-organizing network models publication-title: Neural Networks doi: 10.1016/j.neunet.2004.06.009 – volume: 12 start-page: 2539 issue: Sep year: 2011 ident: 10.1016/j.neunet.2020.06.006_b108 article-title: Weisfeiler-lehman graph kernels publication-title: Journal of Machine Learning Research (JMLR) – year: 2018 ident: 10.1016/j.neunet.2020.06.006_b7 – volume: 20 start-page: 61 issue: 1 year: 2009 ident: 10.1016/j.neunet.2020.06.006_b103 article-title: The graph neural network model publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2008.2005605 – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b37 article-title: Graph adversarial training: Dynamically regularizing based on graph structure publication-title: IEEE Transactions on Knowledge and Data Engineering – start-page: 385 year: 2017 ident: 10.1016/j.neunet.2020.06.006_b98 article-title: Struc2vec: Learning node representations from structural identity – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b69 article-title: Latent adversarial training of graph convolution networks – ident: 10.1016/j.neunet.2020.06.006_b18 – ident: 10.1016/j.neunet.2020.06.006_b91 – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b129 – volume: 29 start-page: 5592 issue: 11 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b140 article-title: Concept drift and anomaly detection in graph streams publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2018.2804443 – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b39 article-title: Fast graph representation learning with PyTorch Geometric – volume: 217 start-page: 117 year: 2014 ident: 10.1016/j.neunet.2020.06.006_b40 article-title: Klog: A language for logical and relational learning with kernels publication-title: Artificial Intelligence doi: 10.1016/j.artint.2014.08.003 – ident: 10.1016/j.neunet.2020.06.006_b127 doi: 10.1609/aaai.v32i1.11872 – volume: 17 start-page: 1109 issue: 5 year: 2005 ident: 10.1016/j.neunet.2020.06.006_b56 article-title: Universal approximation capability of cascade correlation for structures publication-title: Neural Computation doi: 10.1162/0899766053491878 – volume: 35 start-page: 503 issue: 3 year: 2005 ident: 10.1016/j.neunet.2020.06.006_b94 article-title: Self-organizing maps for learning the edit costs in graph matching publication-title: IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics) doi: 10.1109/TSMCB.2005.846635 – start-page: 294 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b3 article-title: Contextual graph Markov model: A deep and generative approach to graph processing – year: 2016 ident: 10.1016/j.neunet.2020.06.006_b71 article-title: Variational graph auto-encoders – ident: 10.1016/j.neunet.2020.06.006_b38 doi: 10.1609/aaai.v33i01.33013558 – ident: 10.1016/j.neunet.2020.06.006_b100 doi: 10.1609/aaai.v33i01.33011110 – start-page: 701 year: 2014 ident: 10.1016/j.neunet.2020.06.006_b95 article-title: Deepwalk: Online learning of social representations – volume: 23 start-page: 1987 issue: 12 year: 2012 ident: 10.1016/j.neunet.2020.06.006_b6 article-title: Compositional generative mapping for tree-structured data - part I: Bottom-up probabilistic modeling of trees publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2012.2222044 – volume: 72 start-page: 1419 issue: 7–9 year: 2009 ident: 10.1016/j.neunet.2020.06.006_b53 article-title: Graph self-organizing maps for cyclic and unbounded graphs publication-title: Neurocomputing doi: 10.1016/j.neucom.2008.12.021 – ident: 10.1016/j.neunet.2020.06.006_b67 doi: 10.24963/ijcai.2019/366 – ident: 10.1016/j.neunet.2020.06.006_b90 doi: 10.18653/v1/W18-5101 – volume: 185 start-page: 105020 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b134 article-title: A deeper graph neural network for recommender systems publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2019.105020 – volume: 91 issue: 1 year: 1991 ident: 10.1016/j.neunet.2020.06.006_b61 article-title: Untersuchungen zu dynamischen neuronalen netzen publication-title: Diploma, Technische Universität München – ident: 10.1016/j.neunet.2020.06.006_b136 – ident: 10.1016/j.neunet.2020.06.006_b110 doi: 10.1109/CVPR.2017.11 – ident: 10.1016/j.neunet.2020.06.006_b119 – volume: 20 start-page: 273 issue: 3 year: 1995 ident: 10.1016/j.neunet.2020.06.006_b25 article-title: Support-vector networks publication-title: Machine Learning doi: 10.1007/BF00994018 – ident: 10.1016/j.neunet.2020.06.006_b111 doi: 10.1007/978-3-030-01418-6_41 – volume: 5 start-page: 157 issue: 2 year: 1994 ident: 10.1016/j.neunet.2020.06.006_b9 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.279181 – volume: 6 start-page: 11 issue: 1 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b144 article-title: Graph convolutional networks: a comprehensive review publication-title: Computational Social Networks doi: 10.1186/s40649-019-0069-y – ident: 10.1016/j.neunet.2020.06.006_b72 – volume: 32 issue: suppl_1 year: 2004 ident: 10.1016/j.neunet.2020.06.006_b105 article-title: BRENDA, the enzyme database: updates and major new developments publication-title: Nucleic Acids Research – volume: 3361 start-page: 1995 issue: 10 year: 1995 ident: 10.1016/j.neunet.2020.06.006_b75 article-title: Convolutional networks for images, speech, and time series publication-title: The Handbook of Brain Theory and Neural Networks – ident: 10.1016/j.neunet.2020.06.006_b70 – volume: 20 start-page: 542 issue: 3 year: 2006 ident: 10.1016/j.neunet.2020.06.006_b22 article-title: Semi-supervised learning publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2009.2015974 – volume: 84 start-page: 317 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b11 article-title: Wild patterns: Ten years after the rise of adversarial machine learning publication-title: Pattern Recognition doi: 10.1016/j.patcog.2018.07.023 – ident: 10.1016/j.neunet.2020.06.006_b49 – ident: 10.1016/j.neunet.2020.06.006_b64 – ident: 10.1016/j.neunet.2020.06.006_b112 – start-page: 294 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b2 article-title: A non-negative factorization approach to node pooling in graph convolutional neural networks – ident: 10.1016/j.neunet.2020.06.006_b29 – ident: 10.1016/j.neunet.2020.06.006_b8 doi: 10.18653/v1/P18-1026 – volume: 15 start-page: 1396 issue: 6 year: 2004 ident: 10.1016/j.neunet.2020.06.006_b88 article-title: Contextual processing of structured data by recursive cascade correlation publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2004.837783 – ident: 10.1016/j.neunet.2020.06.006_b35 – volume: 34 start-page: i457 issue: 13 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b146 article-title: Modeling polypharmacy side effects with graph convolutional networks publication-title: Bioinformatics doi: 10.1093/bioinformatics/bty294 – volume: 12 start-page: 117 issue: 1–2 year: 2000 ident: 10.1016/j.neunet.2020.06.006_b10 article-title: Application of cascade correlation networks for structures to chemistry publication-title: Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies doi: 10.1023/A:1008368105614 – ident: 10.1016/j.neunet.2020.06.006_b96 – ident: 10.1016/j.neunet.2020.06.006_b21 – volume: 21 start-page: i47 issue: suppl_1 year: 2005 ident: 10.1016/j.neunet.2020.06.006_b17 article-title: Protein function prediction via graph kernels publication-title: Bioinformatics doi: 10.1093/bioinformatics/bti1007 – ident: 10.1016/j.neunet.2020.06.006_b45 doi: 10.1609/aaai.v34i04.5803 – volume: 35 start-page: 4979 issue: 23 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b66 article-title: FP2VEC: A new molecular featurizer for learning molecular properties publication-title: Bioinformatics doi: 10.1093/bioinformatics/btz307 – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b4 article-title: Edge-based sequential graph generation with recurrent neural networks publication-title: Neurocomputing – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b36 article-title: Conditional labeled graph generation with GANs – ident: 10.1016/j.neunet.2020.06.006_b46 – ident: 10.1016/j.neunet.2020.06.006_b114 doi: 10.3115/v1/P15-1150 – volume: 38 start-page: 146 issue: 5 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b126 article-title: Dynamic graph cnn for learning on point clouds publication-title: ACM Transactions on Graphics doi: 10.1145/3326362 – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b42 article-title: Towards graph pooling by edge contraction – volume: 11 start-page: 1201 issue: Apr year: 2010 ident: 10.1016/j.neunet.2020.06.006_b121 article-title: Graph kernels publication-title: Journal of Machine Learning Research (JMLR) – ident: 10.1016/j.neunet.2020.06.006_b130 – ident: 10.1016/j.neunet.2020.06.006_b85 doi: 10.18653/v1/D17-1159 – volume: 29 start-page: 5441 issue: 11 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b16 article-title: Recursive neural networks for density estimation over generalized random graphs publication-title: IEEE Transactions on Neural Networks and Learning Systems doi: 10.1109/TNNLS.2018.2803523 – ident: 10.1016/j.neunet.2020.06.006_b5 – ident: 10.1016/j.neunet.2020.06.006_b32 – volume: 78 start-page: 1464 issue: 9 year: 1990 ident: 10.1016/j.neunet.2020.06.006_b73 article-title: The self-organizing map publication-title: Proceedings of the IEEE doi: 10.1109/5.58325 – volume: 2 start-page: 303 issue: 4 year: 1989 ident: 10.1016/j.neunet.2020.06.006_b26 article-title: Approximation by superpositions of a sigmoidal function publication-title: Mathematics of Control, Signals and Systems doi: 10.1007/BF02551274 – volume: 330 start-page: 771 issue: 4 year: 2003 ident: 10.1016/j.neunet.2020.06.006_b31 article-title: Distinguishing enzyme structures from non-enzymes without alignments publication-title: Journal of Molecular Biology doi: 10.1016/S0022-2836(03)00628-4 – ident: 10.1016/j.neunet.2020.06.006_b78 – volume: 29 start-page: 93 issue: 3 year: 2008 ident: 10.1016/j.neunet.2020.06.006_b106 article-title: Collective classification in network data publication-title: AI Magazine doi: 10.1609/aimag.v29i3.2157 – ident: 10.1016/j.neunet.2020.06.006_b20 – volume: 18 start-page: 1093 issue: 8 year: 2005 ident: 10.1016/j.neunet.2020.06.006_b97 article-title: Graph kernels for chemical informatics publication-title: Neural Networks doi: 10.1016/j.neunet.2005.07.009 – ident: 10.1016/j.neunet.2020.06.006_b14 – ident: 10.1016/j.neunet.2020.06.006_b125 doi: 10.1007/978-3-030-01228-1_25 – ident: 10.1016/j.neunet.2020.06.006_b145 doi: 10.7551/mitpress/7503.003.0205 – volume: 313 start-page: 14 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b116 article-title: Nonparametric small random networks for graph-structured pattern recognition publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.095 – start-page: 1365 year: 2015 ident: 10.1016/j.neunet.2020.06.006_b132 article-title: Deep graph kernels – start-page: 974 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b135 article-title: Graph convolutional neural networks for web-scale recommender systems – ident: 10.1016/j.neunet.2020.06.006_b137 – volume: 34 start-page: 25 issue: 4 year: 2017 ident: 10.1016/j.neunet.2020.06.006_b19 article-title: Geometric deep learning: going beyond Euclidean data publication-title: IEEE Signal Processing Magazine doi: 10.1109/MSP.2017.2693418 – ident: 10.1016/j.neunet.2020.06.006_b118 – volume: 13 start-page: 1469 issue: 14 year: 2007 ident: 10.1016/j.neunet.2020.06.006_b89 article-title: An introduction to recursive neural networks and kernel methods for cheminformatics publication-title: Current Pharmaceutical Design doi: 10.2174/138161207780765981 – volume: 17 start-page: 395 issue: 4 year: 2007 ident: 10.1016/j.neunet.2020.06.006_b122 article-title: A tutorial on spectral clustering publication-title: Statistics and Computing doi: 10.1007/s11222-007-9033-z – ident: 10.1016/j.neunet.2020.06.006_b123 – start-page: 309 year: 2019 ident: 10.1016/j.neunet.2020.06.006_b86 article-title: Safe: Self-attentive function embeddings for binary similarity – ident: 10.1016/j.neunet.2020.06.006_b65 – volume: 8 start-page: 714 issue: 3 year: 1997 ident: 10.1016/j.neunet.2020.06.006_b113 article-title: Supervised neural networks for the classification of structures publication-title: IEEE Transactions on Neural Networks doi: 10.1109/72.572108 – start-page: 1 year: 2010 ident: 10.1016/j.neunet.2020.06.006_b44 article-title: Graph echo state networks – ident: 10.1016/j.neunet.2020.06.006_b23 – ident: 10.1016/j.neunet.2020.06.006_b48 – year: 2019 ident: 10.1016/j.neunet.2020.06.006_b128 article-title: Deep graph library: Towards efficient and scalable deep learning on graphs – start-page: 1250 year: 2016 ident: 10.1016/j.neunet.2020.06.006_b99 article-title: Graph sparsification approaches for laplacian smoothing – ident: 10.1016/j.neunet.2020.06.006_b115 – volume: 2 start-page: 1 issue: 1 year: 1993 ident: 10.1016/j.neunet.2020.06.006_b81 article-title: Random walks on graphs: A survey publication-title: Combinatorics, Paul Erdos is Eighty – start-page: 2847 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b147 article-title: Adversarial attacks on neural networks for graph data – year: 1976 ident: 10.1016/j.neunet.2020.06.006_b15 – volume: 20 start-page: 498 issue: 3 year: 2009 ident: 10.1016/j.neunet.2020.06.006_b87 article-title: Neural network for graphs: A contextual constructive approach publication-title: IEEE Transactions on Neural Networks doi: 10.1109/TNN.2008.2010350 – volume: 46 start-page: 109 year: 2013 ident: 10.1016/j.neunet.2020.06.006_b13 article-title: Recommender systems survey publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2013.03.012 – ident: 10.1016/j.neunet.2020.06.006_b143 doi: 10.24963/ijcai.2018/439 – volume: 37 start-page: 75 issue: 1 year: 1999 ident: 10.1016/j.neunet.2020.06.006_b102 article-title: Mixed memory Markov models: Decomposing complex stochastic processes as mixtures of simpler ones publication-title: Machine Learning doi: 10.1023/A:1007649326333 – ident: 10.1016/j.neunet.2020.06.006_b84 doi: 10.18653/v1/N18-2078 – ident: 10.1016/j.neunet.2020.06.006_b34 – ident: 10.1016/j.neunet.2020.06.006_b51 – volume: 5 start-page: 17 issue: 1 year: 1960 ident: 10.1016/j.neunet.2020.06.006_b33 article-title: On the evolution of random graphs publication-title: Publications of the Mathematical Institute of the Hungarian Academy of Science – start-page: 593 year: 2018 ident: 10.1016/j.neunet.2020.06.006_b104 article-title: Modeling relational data with graph convolutional networks – volume: 29 start-page: 1944 issue: 11 year: 2007 ident: 10.1016/j.neunet.2020.06.006_b30 article-title: Weighted graph cuts without eigenvectors a multilevel approach publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2007.1115 – start-page: 855 year: 2016 ident: 10.1016/j.neunet.2020.06.006_b50 article-title: Node2vec: Scalable feature learning for networks – volume: 34 start-page: 786 issue: 2 year: 1991 ident: 10.1016/j.neunet.2020.06.006_b28 article-title: Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds correlation with molecular orbital energies and hydrophobicity publication-title: Journal of Medicinal Chemistry doi: 10.1021/jm00106a046 – ident: 10.1016/j.neunet.2020.06.006_b76 – ident: 10.1016/j.neunet.2020.06.006_b109 |
| SSID | ssj0006843 |
| Score | 2.6761327 |
| SecondaryResourceType | review_article |
| Snippet | The adaptive processing of graph data is a long-standing research topic that has been lately consolidated as a theme of major interest in the deep learning... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 203 |
| SubjectTerms | Deep learning for graphs Graph neural networks Learning for structured data |
| Title | A gentle introduction to deep learning for graphs |
| URI | https://dx.doi.org/10.1016/j.neunet.2020.06.006 https://www.proquest.com/docview/2415299399 |
| Volume | 129 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NS8MwFA9jXrz4LX6OCF7j0jZNk-MYjqm4iw52C81HZTK64bqrf7t5aasoguAxJS-Ul7wPkt_7PYSuE2q1zowghRAGWphRopmMSBzxPM2zyPHwYvo44eMpu5-lsw4atrUwAKtsfH_t04O3br70G232V_N5_4n6UMuhVNSfU293UFHOWAb8-TfvXzAPLmrknJ9MYHZbPhcwXqXblA4QlTENLJ7Q9-j38PTDUYfoM9pDO03aiAf1n-2jjisP0G7bkgE3FnqIogGGWqmFw3OAoNuaGxZXS2ydW-GmR8QL9qkqDlzV6yM0Hd0-D8ek6YpATCLSitiIF5H2gZsaJmSh4UZCF3mcapdYWki4GcoLn1XllNlYcijmdlRnWRrrxHmLPkbdclm6E4QdNzJNgPFLC5bzSBttrRTMpM6PY36KklYZyjSU4dC5YqFabNirqlWoQIUqQOS8FPmUWtWUGX_Mz1o9q29br7xX_0Pyqt0W5a0Cnjry0i03axXyEp96SXn279XP0TaMakDZBepWbxt36TOQSvfCEeuhrcHdw3jyAdK72Xw |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA61HvTiW3wbweva7CPZ5FiKUrXtxRZ6C5tsViplW2x79bebyWYVRSh43OzMskzmRfLNDEK3McmVSjUPCs41jDAjgUpEGEQhy2iWhoa5G9P-gHVHydOYjhuoU9fCAKzS-_7Kpztv7VdaXpqt-WTSeiE21DIoFbV6au0u3UCbCY1TUO27j2-cB-MVdM5SB0Be1885kFdpVqUBSGVEXBtPGHz0d3z65ald-HnYQzs-b8Tt6tf2UcOUB2i3nsmAvYkeorCNoVhqavAEMOh51RwWL2c4N2aO_ZCIV2xzVeyaVS-O0OjhftjpBn4sQqBjTpdBHrIiVDZyE51wUSg4klBFFlFl4pwUAo6GssKmVRlJ8kgwqOY2RKUpjVRsrEkfo2Y5K80JwoZpQWNo-aV4krFQaZXngieaGvscsVMU18KQ2vcMh9EVU1mDw95kJUIJIpQOI2e5gi-uedUzYw19WstZ_th7ad36Gs6belukNQu468hKM1stpEtMbO4lxNm_v36NtrrDfk_2HgfP52gb3lTosgvUXL6vzKVNR5bqyqnbJwDO2xI |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+gentle+introduction+to+deep+learning+for+graphs&rft.jtitle=Neural+networks&rft.au=Bacciu%2C+Davide&rft.au=Errica%2C+Federico&rft.au=Micheli%2C+Alessio&rft.au=Podda%2C+Marco&rft.date=2020-09-01&rft.issn=0893-6080&rft.volume=129&rft.spage=203&rft.epage=221&rft_id=info:doi/10.1016%2Fj.neunet.2020.06.006&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neunet_2020_06_006 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |