Feature propagation as self-supervision signals on graphs
Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on graphs. Current algorithms are based on contrastive learning, which is computationally and memory expensive, and the assumption of invariance under...
Saved in:
Published in | Knowledge-based systems Vol. 289; p. 111512 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
08.04.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on graphs. Current algorithms are based on contrastive learning, which is computationally and memory expensive, and the assumption of invariance under certain graph augmentations. However, graph transformations such as edge sampling may modify the semantics of the data, potentially leading to inaccurate invariance assumptions. To address these limitations, we introduce Regularized Graph Infomax (RGI), a simple yet effective framework for node level self-supervised learning that trains a graph neural network encoder by maximizing the mutual information between the output node embeddings and their propagation through the graph, which encode the nodes’ local and global context, respectively. RGI generates self-supervision signals through feature propagation rather than relying on graph data augmentations. Furthermore, the method is non-contrastive and does not depend on a two branch architecture. We run RGI on both transductive and inductive settings with popular graph benchmarks and show that it can achieve state-of-the-art performance regardless of its simplicity.
•We present Regularized Graph Infomax (RGI) for efficient graph self-supervised learning.•RGI generates self-supervision signals with feature propagation.•The method does not use graph data augmentations and is non-contrastive.•State of the art performance is achieved in both transductive and inductive tasks. |
---|---|
AbstractList | Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on graphs. Current algorithms are based on contrastive learning, which is computationally and memory expensive, and the assumption of invariance under certain graph augmentations. However, graph transformations such as edge sampling may modify the semantics of the data, potentially leading to inaccurate invariance assumptions. To address these limitations, we introduce Regularized Graph Infomax (RGI), a simple yet effective framework for node level self-supervised learning that trains a graph neural network encoder by maximizing the mutual information between the output node embeddings and their propagation through the graph, which encode the nodes’ local and global context, respectively. RGI generates self-supervision signals through feature propagation rather than relying on graph data augmentations. Furthermore, the method is non-contrastive and does not depend on a two branch architecture. We run RGI on both transductive and inductive settings with popular graph benchmarks and show that it can achieve state-of-the-art performance regardless of its simplicity.
•We present Regularized Graph Infomax (RGI) for efficient graph self-supervised learning.•RGI generates self-supervision signals with feature propagation.•The method does not use graph data augmentations and is non-contrastive.•State of the art performance is achieved in both transductive and inductive tasks. |
ArticleNumber | 111512 |
Author | Pina, Oscar Vilaplana, Verónica |
Author_xml | – sequence: 1 givenname: Oscar orcidid: 0009-0003-9755-6629 surname: Pina fullname: Pina, Oscar email: oscar.pina@upc.edu – sequence: 2 givenname: Verónica orcidid: 0000-0001-6924-9961 surname: Vilaplana fullname: Vilaplana, Verónica email: veronica.vilaplana@upc.edu |
BookMark | eNp9j0FLw0AQhRepYFv9Bx7yBxJ3tjvd7EWQYq1Q8KLnZd1M6taahJ200H9vSjx7eW948B7zzcSkaRsS4h5kARKWD_viu2n5zIWSShcAgKCuxBRKo3KjpZ2IqbQocyMRbsSMeS-lVArKqbBr8v0xUdaltvM738e2yTxnTIc652NH6RT5knHcNf7A2XDuku---FZc10NAd38-Fx_r5_fVJt--vbyunrZ5WEjoB7UGl4NoNDZ45ZWuCG1dY4XeUDC6XFr1SbIuAxisKlKIUBn0iLoMajEXetwNqWVOVLsuxR-fzg6ku-C7vRvx3QXfjfhD7XGs0fDbKVJyHCI1gaqYKPSuauP_A7_olmdn |
Cites_doi | 10.1162/neco.1995.7.6.1129 10.1016/j.jmsy.2023.05.006 10.1145/3534678.3539321 10.1186/s40537-019-0197-0 10.1093/bioinformatics/btx252 10.1109/2.36 10.1109/ICCV48922.2021.00951 10.1145/3366423.3380112 |
ContentType | Journal Article |
Copyright | 2024 The Authors |
Copyright_xml | – notice: 2024 The Authors |
DBID | 6I. AAFTH AAYXX CITATION |
DOI | 10.1016/j.knosys.2024.111512 |
DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 1872-7409 |
ExternalDocumentID | 10_1016_j_knosys_2024_111512 S0950705124001473 |
GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5VS 6I. 7-5 71M 77K 8P~ 9JN AACTN AAEDT AAEDW AAFTH AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABAOU ABBOA ABIVO ABJNI ABMAC ABMYL ABYKQ ACAZW ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADGUI ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 RIG ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SST SSV SSW SSZ T5K WH7 XPP ZMT ~02 ~G- 29L AAQXK AAXKI AAYXX ABXDB ACNNM ADJOM ADMUD AFJKZ ASPBG AVWKF AZFZN CITATION EJD FEDTE FGOYB G-2 G8K HLZ HVGLF HZ~ LG9 LY7 M41 R2- SBC SET UHS WUQ |
ID | FETCH-LOGICAL-c301t-c397563974579ca2a24de59ff5d5a7ec748692be0f8c175dde2551d75a5548c23 |
IEDL.DBID | AIKHN |
ISSN | 0950-7051 |
IngestDate | Thu Sep 26 16:18:48 EDT 2024 Sat Mar 16 16:14:10 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Graph representation learning Regularization Graph neural network Self-supervised learning |
Language | English |
License | This is an open access article under the CC BY-NC-ND license. |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c301t-c397563974579ca2a24de59ff5d5a7ec748692be0f8c175dde2551d75a5548c23 |
ORCID | 0000-0001-6924-9961 0009-0003-9755-6629 |
OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S0950705124001473 |
ParticipantIDs | crossref_primary_10_1016_j_knosys_2024_111512 elsevier_sciencedirect_doi_10_1016_j_knosys_2024_111512 |
PublicationCentury | 2000 |
PublicationDate | 2024-04-08 |
PublicationDateYYYYMMDD | 2024-04-08 |
PublicationDate_xml | – month: 04 year: 2024 text: 2024-04-08 day: 08 |
PublicationDecade | 2020 |
PublicationTitle | Knowledge-based systems |
PublicationYear | 2024 |
Publisher | Elsevier B.V |
Publisher_xml | – name: Elsevier B.V |
References | Linsker (b19) 1988; 21 Chen, Kornblith, Norouzi, Hinton (b1) 2020 Zitnik, Leskovec (b39) 2017; 33 Z. Peng, W. Huang, M. Luo, Q. Zheng, Y. Rong, T. Xu, J. Huang, Graph Representation Learning via Graphical Mutual Information Maximization, in: Proceedings of the Web Conference, 2020 Wang, Zhang, Zhu, Huang (b18) 2022 Zbontar, Jing, Misra, LeCun, Deny (b5) 2021 Shwartz-Ziv, Balestriero, LeCun (b25) 2022 Hu, Fey, Zitnik, Dong, Ren, Liu, Catasta, Leskovec (b28) 2021 Bell, Sejnowski (b20) 1995; 7 R.D. Hjelm, A. Fedorov, S. Lavoie-Marchildon, K. Grewal, P. Bachman, A. Trischler, Y. Bengio, Learning deep representations by mutual information estimation and maximization, in: International Conference on Learning Representations, 2019, URL. Grill, Strub, Altché, Tallec, Richemond, Buchatskaya, Doersch, Pires, Guo, Azar, Piot, Kavukcuoglu, Munos, Valko (b2) 2020 McAuley, Targett, Shi, van den Hengel (b37) 2015 Hua, Wang, Xue, Wang, Ren, Zhao (b27) 2021 Shorten, Khoshgoftaar (b7) 2019; 6 Li, Yu, Lei, Li, Yang (b8) 2023 Ioffe, Szegedy (b29) 2015 Kingma, Ba (b36) 2015 M. Caron, H. Touvron, I. Misra, H. Jégou, J. Mairal, P. Bojanowski, A. Joulin, Emerging Properties in Self-Supervised Vision Transformers, in: Proceedings of the International Conference on Computer Vision, ICCV, 2021. F.-Y. Sun, J. Hoffman, V. Verma, J. Tang, InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization, in: International Conference on Learning Representations, 2019. Bielak, Kajdanowicz, Chawla (b12) 2021 Paszke, Gross, Chintala, Chanan, Yang, DeVito, Lin, Desmaison, Antiga, Lerer (b33) 2017 Thakoor, Tallec, Azar, Azabou, Dyer, Munos, Veličković, Valko (b10) 2021 Y. Zhu, Y. Xu, F. Yu, Q. Liu, S. Wu, L. Wang, Deep Graph Contrastive Representation Learning, in: ICML Workshop on Graph Representation Learning and beyond, 2020, URL. Z. Hou, X. Liu, Y. Cen, Y. Dong, H. Yang, C. Wang, J. Tang, GraphMAE: Self-Supervised Masked Graph Autoencoders, in: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 594–604. H. Zhang, Q. Wu, J. Yan, D. Wipf, S.Y. Philip, From canonical correlation analysis to self-supervised graph neural networks, in: Thirty-Fifth Conference on Neural Information Processing Systems, 2021. T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: International Conference on Learning Representations, 2017, URL. Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel, Blondel, Prettenhofer, Weiss, Dubourg, Vanderplas, Passos, Cournapeau, Brucher, Perrot, Duchesnay (b35) 2011; 12 Xu, Cheng, Luo, Chen, Zhang (b14) 2021; Vol. 34 M. Fey, J.E. Lenssen, Fast Graph Representation Learning with PyTorch Geometric, in: ICLR Workshop on Representation Learning on Graphs and Manifolds, 2019. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, Y. Bengio, Graph attention networks, in: International Conference on Learning Representations, 2018, URL. . M. Tschannen, J. Djolonga, P.K. Rubenstein, S. Gelly, M. Lucic, On Mutual Information Maximization for Representation Learning, in: International Conference on Learning Representations, 2020, URL. Bardes, Ponce, LeCun (b6) 2022 Lee, Lee, Park (b17) 2022 P. Veličković, W. Fedus, W.L. Hamilton, P. Liò, Y. Bengio, R.D. Hjelm, Deep Graph Infomax, in: International Conference on Learning Representations, 2019, URL. Oquab, Darcet, Moutakanni, Vo, Szafraniec, Khalidov, Fernandez, Haziza, Massa, El-Nouby, Howes, Huang, Xu, Sharma, Li, Galuba, Rabbat, Assran, Ballas, Synnaeve, Misra, Jegou, Mairal, Labatut, Joulin, Bojanowski (b4) 2023 Sinha, Shen, Song, Ma, Eide, Hsu, Wang (b38) 2015 K. Hassani, A.H. Khasahmadi, Contrastive Multi-View Representation Learning on Graphs, in: Proceedings of International Conference on Machine Learning, 2020, pp. 3451–3461. Hamilton, Ying, Leskovec (b32) 2017; Vol. 30 Li, Zhang, Li, Zhang (b9) 2023; 68 10.1016/j.knosys.2024.111512_b30 10.1016/j.knosys.2024.111512_b31 10.1016/j.knosys.2024.111512_b16 Ioffe (10.1016/j.knosys.2024.111512_b29) 2015 10.1016/j.knosys.2024.111512_b15 Bell (10.1016/j.knosys.2024.111512_b20) 1995; 7 10.1016/j.knosys.2024.111512_b34 Li (10.1016/j.knosys.2024.111512_b9) 2023; 68 10.1016/j.knosys.2024.111512_b13 10.1016/j.knosys.2024.111512_b11 Lee (10.1016/j.knosys.2024.111512_b17) 2022 Paszke (10.1016/j.knosys.2024.111512_b33) 2017 Zbontar (10.1016/j.knosys.2024.111512_b5) 2021 Hu (10.1016/j.knosys.2024.111512_b28) 2021 Grill (10.1016/j.knosys.2024.111512_b2) 2020 Thakoor (10.1016/j.knosys.2024.111512_b10) 2021 Wang (10.1016/j.knosys.2024.111512_b18) 2022 Sinha (10.1016/j.knosys.2024.111512_b38) 2015 Kingma (10.1016/j.knosys.2024.111512_b36) 2015 Oquab (10.1016/j.knosys.2024.111512_b4) 2023 Shorten (10.1016/j.knosys.2024.111512_b7) 2019; 6 Hua (10.1016/j.knosys.2024.111512_b27) 2021 Bardes (10.1016/j.knosys.2024.111512_b6) 2022 10.1016/j.knosys.2024.111512_b26 Pedregosa (10.1016/j.knosys.2024.111512_b35) 2011; 12 Chen (10.1016/j.knosys.2024.111512_b1) 2020 10.1016/j.knosys.2024.111512_b23 Hamilton (10.1016/j.knosys.2024.111512_b32) 2017; Vol. 30 10.1016/j.knosys.2024.111512_b24 10.1016/j.knosys.2024.111512_b21 10.1016/j.knosys.2024.111512_b22 Bielak (10.1016/j.knosys.2024.111512_b12) 2021 Shwartz-Ziv (10.1016/j.knosys.2024.111512_b25) 2022 Xu (10.1016/j.knosys.2024.111512_b14) 2021; Vol. 34 McAuley (10.1016/j.knosys.2024.111512_b37) 2015 10.1016/j.knosys.2024.111512_b3 Linsker (10.1016/j.knosys.2024.111512_b19) 1988; 21 Zitnik (10.1016/j.knosys.2024.111512_b39) 2017; 33 Li (10.1016/j.knosys.2024.111512_b8) 2023 |
References_xml | – year: 2022 ident: b18 article-title: Augmentation-free graph contrastive learning with performance guarantee contributor: fullname: Huang – year: 2015 ident: b36 article-title: Adam: A method for stochastic optimization publication-title: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings contributor: fullname: Ba – volume: 7 start-page: 1129 year: 1995 end-page: 1159 ident: b20 article-title: An information-maximization approach to blind separation and blind deconvolution publication-title: Neural Comput. contributor: fullname: Sejnowski – year: 2020 ident: b2 article-title: Bootstrap your own latent: A new approach to self-supervised learning contributor: fullname: Valko – year: 2022 ident: b17 article-title: Augmentation-free self-supervised learning on graphs publication-title: AAAI contributor: fullname: Park – start-page: 43 year: 2015 end-page: 52 ident: b37 article-title: Image-based recommendations on styles and substitutes publication-title: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval contributor: fullname: van den Hengel – year: 2017 ident: b33 article-title: Automatic differentiation in pytorch contributor: fullname: Lerer – year: 2021 ident: b10 article-title: Large-scale representation learning on graphs via bootstrapping contributor: fullname: Valko – volume: 68 start-page: 523 year: 2023 end-page: 535 ident: b9 article-title: Federated transfer learning in fault diagnosis under data privacy with target self-adaptation publication-title: J. Manuf. Syst. contributor: fullname: Zhang – volume: 12 start-page: 2825 year: 2011 end-page: 2830 ident: b35 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. contributor: fullname: Duchesnay – year: 2023 ident: b4 article-title: DINOv2: Learning robust visual features without supervision contributor: fullname: Bojanowski – volume: Vol. 34 start-page: 30414 year: 2021 end-page: 30425 ident: b14 article-title: Infogcl: Information-aware graph contrastive learning publication-title: Advances in Neural Information Processing Systems contributor: fullname: Zhang – volume: Vol. 30 year: 2017 ident: b32 article-title: Inductive representation learning on large graphs publication-title: Advances in Neural Information Processing Systems contributor: fullname: Leskovec – year: 2021 ident: b5 article-title: Barlow twins: Self-supervised learning via redundancy reduction contributor: fullname: Deny – volume: 33 start-page: 190 year: 2017 end-page: 198 ident: b39 article-title: Predicting multicellular function through multi-layer tissue networks publication-title: Bioinformatics contributor: fullname: Leskovec – year: 2022 ident: b25 article-title: What do we maximize in self-supervised learning? contributor: fullname: LeCun – volume: 6 start-page: 1 year: 2019 end-page: 48 ident: b7 article-title: A survey on image data augmentation for deep learning publication-title: J. Big Data contributor: fullname: Khoshgoftaar – volume: 21 start-page: 105 year: 1988 end-page: 117 ident: b19 article-title: Self-organization in a perceptual network publication-title: Computer contributor: fullname: Linsker – year: 2021 ident: b12 article-title: Graph barlow twins: A self-supervised representation learning framework for graphs contributor: fullname: Chawla – start-page: 243 year: 2015 end-page: 246 ident: b38 article-title: An overview of microsoft academic service (MAS) and applications publication-title: Proceedings of the 24th International Conference on World Wide Web contributor: fullname: Wang – year: 2022 ident: b6 article-title: Vicreg: Variance-invariance-covariance regularization for self-supervised learning publication-title: ICLR contributor: fullname: LeCun – year: 2020 ident: b1 article-title: A simple framework for contrastive learning of visual representations contributor: fullname: Hinton – start-page: 448 year: 2015 end-page: 456 ident: b29 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 contributor: fullname: Szegedy – year: 2021 ident: b27 article-title: On feature decorrelation in self-supervised learning contributor: fullname: Zhao – year: 2023 ident: b8 article-title: Intelligent machinery fault diagnosis with event-based camera publication-title: IEEE Trans. Ind. Inform. contributor: fullname: Yang – year: 2021 ident: b28 article-title: Open graph benchmark: Datasets for machine learning on graphs contributor: fullname: Leskovec – volume: 7 start-page: 1129 issue: 6 year: 1995 ident: 10.1016/j.knosys.2024.111512_b20 article-title: An information-maximization approach to blind separation and blind deconvolution publication-title: Neural Comput. doi: 10.1162/neco.1995.7.6.1129 contributor: fullname: Bell – year: 2021 ident: 10.1016/j.knosys.2024.111512_b5 contributor: fullname: Zbontar – year: 2017 ident: 10.1016/j.knosys.2024.111512_b33 contributor: fullname: Paszke – year: 2015 ident: 10.1016/j.knosys.2024.111512_b36 article-title: Adam: A method for stochastic optimization contributor: fullname: Kingma – ident: 10.1016/j.knosys.2024.111512_b11 – ident: 10.1016/j.knosys.2024.111512_b34 – ident: 10.1016/j.knosys.2024.111512_b15 – volume: 68 start-page: 523 year: 2023 ident: 10.1016/j.knosys.2024.111512_b9 article-title: Federated transfer learning in fault diagnosis under data privacy with target self-adaptation publication-title: J. Manuf. Syst. doi: 10.1016/j.jmsy.2023.05.006 contributor: fullname: Li – ident: 10.1016/j.knosys.2024.111512_b13 – year: 2023 ident: 10.1016/j.knosys.2024.111512_b8 article-title: Intelligent machinery fault diagnosis with event-based camera publication-title: IEEE Trans. Ind. Inform. contributor: fullname: Li – ident: 10.1016/j.knosys.2024.111512_b21 – ident: 10.1016/j.knosys.2024.111512_b30 doi: 10.1145/3534678.3539321 – ident: 10.1016/j.knosys.2024.111512_b23 – year: 2021 ident: 10.1016/j.knosys.2024.111512_b10 contributor: fullname: Thakoor – year: 2023 ident: 10.1016/j.knosys.2024.111512_b4 contributor: fullname: Oquab – volume: 6 start-page: 1 year: 2019 ident: 10.1016/j.knosys.2024.111512_b7 article-title: A survey on image data augmentation for deep learning publication-title: J. Big Data doi: 10.1186/s40537-019-0197-0 contributor: fullname: Shorten – year: 2022 ident: 10.1016/j.knosys.2024.111512_b17 article-title: Augmentation-free self-supervised learning on graphs contributor: fullname: Lee – start-page: 448 year: 2015 ident: 10.1016/j.knosys.2024.111512_b29 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift contributor: fullname: Ioffe – year: 2020 ident: 10.1016/j.knosys.2024.111512_b1 contributor: fullname: Chen – start-page: 43 year: 2015 ident: 10.1016/j.knosys.2024.111512_b37 article-title: Image-based recommendations on styles and substitutes contributor: fullname: McAuley – volume: 12 start-page: 2825 year: 2011 ident: 10.1016/j.knosys.2024.111512_b35 article-title: Scikit-learn: Machine learning in python publication-title: J. Mach. Learn. Res. contributor: fullname: Pedregosa – year: 2021 ident: 10.1016/j.knosys.2024.111512_b27 contributor: fullname: Hua – ident: 10.1016/j.knosys.2024.111512_b31 – year: 2022 ident: 10.1016/j.knosys.2024.111512_b6 article-title: Vicreg: Variance-invariance-covariance regularization for self-supervised learning contributor: fullname: Bardes – year: 2020 ident: 10.1016/j.knosys.2024.111512_b2 contributor: fullname: Grill – volume: 33 start-page: 190 issue: 14 year: 2017 ident: 10.1016/j.knosys.2024.111512_b39 article-title: Predicting multicellular function through multi-layer tissue networks publication-title: Bioinformatics doi: 10.1093/bioinformatics/btx252 contributor: fullname: Zitnik – volume: Vol. 30 year: 2017 ident: 10.1016/j.knosys.2024.111512_b32 article-title: Inductive representation learning on large graphs contributor: fullname: Hamilton – volume: Vol. 34 start-page: 30414 year: 2021 ident: 10.1016/j.knosys.2024.111512_b14 article-title: Infogcl: Information-aware graph contrastive learning contributor: fullname: Xu – year: 2021 ident: 10.1016/j.knosys.2024.111512_b12 contributor: fullname: Bielak – volume: 21 start-page: 105 issue: 3 year: 1988 ident: 10.1016/j.knosys.2024.111512_b19 article-title: Self-organization in a perceptual network publication-title: Computer doi: 10.1109/2.36 contributor: fullname: Linsker – ident: 10.1016/j.knosys.2024.111512_b22 – ident: 10.1016/j.knosys.2024.111512_b3 doi: 10.1109/ICCV48922.2021.00951 – ident: 10.1016/j.knosys.2024.111512_b24 – year: 2022 ident: 10.1016/j.knosys.2024.111512_b25 contributor: fullname: Shwartz-Ziv – start-page: 243 year: 2015 ident: 10.1016/j.knosys.2024.111512_b38 article-title: An overview of microsoft academic service (MAS) and applications contributor: fullname: Sinha – ident: 10.1016/j.knosys.2024.111512_b26 – ident: 10.1016/j.knosys.2024.111512_b16 doi: 10.1145/3366423.3380112 – year: 2022 ident: 10.1016/j.knosys.2024.111512_b18 contributor: fullname: Wang – year: 2021 ident: 10.1016/j.knosys.2024.111512_b28 contributor: fullname: Hu |
SSID | ssj0002218 |
Score | 2.4392338 |
Snippet | Self-supervised learning is gaining considerable attention as a solution to avoid the requirement of extensive annotations in representation learning on... |
SourceID | crossref elsevier |
SourceType | Aggregation Database Publisher |
StartPage | 111512 |
SubjectTerms | Graph neural network Graph representation learning Regularization Self-supervised learning |
Title | Feature propagation as self-supervision signals on graphs |
URI | https://dx.doi.org/10.1016/j.knosys.2024.111512 |
Volume | 289 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwED71sbDwRpRH5YHVFLt27YxVRVVA6gKVukW2Y0sFVKqmHVj47ZzzQCAhBpYoiXJS9OXuuy_2-Qxw5bRMbCyrwPRuqGDMUm2lod5iPtPBqMwV3T6ng8lM3M_lvAGjei1MLKusuL_k9IKtqzu9Cs3earHoPaI4QH_FhCWizlf9JrQxHQnRgvbw7mEy_SJkzothvvg8jQb1CrqizOtl-Za_x77dXET6kIz_nqG-ZZ3xPuxWcpEMyzc6gIZfHsJevRUDqSLzCJIo5bZrT5AQkSIKuInJSe5fA823q8gIcVyMxHoN9DiCp0Wv6vwYZuPbp9GEVrsiUIfBuMFjomScjhNSJc5ww0XmZRKCzKRR3imhBwm3_iZoh9oA6Qv_GlimpEHloB3vn0Br-bb0p0CkxWjUA6FZyAT3zgYULEw4y5PA-kJ3gNZIpKuy-UVaV4U9pyVyaUQuLZHrgKrhSn98xBT5-U_Ls39bnsNOvCqKafQFtDbrrb9EnbCxXWhef7Bu5Q2fDUm8RA |
link.rule.ids | 315,786,790,4521,24144,27955,27956,45618,45712 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV27TsMwFLVKGWDhjShPD6ymxLVrZ0QVVYHShVbqZtmOLfFQWjXtwMK3c-0kAiTEwBJFiS1FJ77nnjjH1whdWslTE2wVkN41YUliiDRcE2cgn0mvRWZjtc9RdzBh91M-baBevRYm2Cor7i85PbJ1daVdodmePz-3n0AcwHiFhMWCzhedNbQe1EDwdV19fPk8KI2TfKE1Cc3r9XPR5PWaz4r3ULWbskAePKG_56dvOae_g7YqsYhvyufZRQ2X76HteiMGXMXlPkqDkFstHAY6BIKIYGNd4MK9eVKs5oEPwqwYDm4NGG8YTmOl6uIATfq3496AVHsiEAuhuIRjKnj4Gce4SK2mmrLM8dR7nnEtnBVMdlNq3LWXFpQBkBd8MySZ4Bp0g7S0c4ia-Sx3RwhzA7Eou0wmPmPUWeNBriTMGpr6pMNkC5EaCTUvS1-o2hP2okrkVEBOlci1kKjhUj9eoQJ2_rPn8b97XqCNwfhxqIZ3o4cTtBnuRFuNPEXN5WLlzkAxLM15HBGfsaC9GQ |
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=Feature+propagation+as+self-supervision+signals+on+graphs&rft.jtitle=Knowledge-based+systems&rft.au=Pina%2C+Oscar&rft.au=Vilaplana%2C+Ver%C3%B3nica&rft.date=2024-04-08&rft.issn=0950-7051&rft.volume=289&rft.spage=111512&rft_id=info:doi/10.1016%2Fj.knosys.2024.111512&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_knosys_2024_111512 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon |