Towards Personalized Federated Learning
In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preservin...
Saved in:
| Published in | IEEE transaction on neural networks and learning systems Vol. 34; no. 12; pp. 9587 - 9603 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.12.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches. |
|---|---|
| AbstractList | In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches.In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches. In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data privacy. Recent significant developments in the data regulation landscape have prompted a seismic shift in interest toward privacy-preserving AI. This has contributed to the popularity of Federated Learning (FL), the leading paradigm for the training of machine learning models on data silos in a privacy-preserving manner. In this survey, we explore the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets. We analyze the key motivations for PFL and present a unique taxonomy of PFL techniques categorized according to the key challenges and personalization strategies in PFL. We highlight their key ideas, challenges, opportunities, and envision promising future trajectories of research toward a new PFL architectural design, realistic PFL benchmarking, and trustworthy PFL approaches. |
| Author | Tan, Alysa Ziying Yu, Han Cui, Lizhen Yang, Qiang |
| Author_xml | – sequence: 1 givenname: Alysa Ziying orcidid: 0000-0003-0084-3473 surname: Tan fullname: Tan, Alysa Ziying organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore – sequence: 2 givenname: Han orcidid: 0000-0001-6893-8650 surname: Yu fullname: Yu, Han email: han.yu@ntu.edu.sg organization: School of Computer Science and Engineering, Nanyang Technological University, Singapore – sequence: 3 givenname: Lizhen orcidid: 0000-0002-8262-8883 surname: Cui fullname: Cui, Lizhen email: clz@sdu.edu.cn organization: School of Software, Shandong University, Jinan, China – sequence: 4 givenname: Qiang orcidid: 0000-0001-5059-8360 surname: Yang fullname: Yang, Qiang email: qyang@cse.ust.hk organization: Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35344498$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kE1Lw0AQhhep2Fr7BxSk4EEvrfuR_TpKsSqEKljB27JJJpKSJnU3QfTXu7Ufhx6cywzL8w6zzynqVHUFCJ0TPCYE69v5bBa_jimmdMyIwELrI9SjRNARZUp19rN876KB9wscSmAuIn2CuoyzKIq06qHref1lXeaHL-B8Xdmy-IFsOIUMnG3CFIN1VVF9nKHj3JYeBtveR2_T-_nkcRQ_PzxN7uJRSoVoRjYXVmDGuZA8iWQEGaZJuEdoqZIkSgnnKpG5lhljLCfYJkrmaYoVJTaB8NpHN5u9K1d_tuAbsyx8CmVpK6hbb6gIdwvKhAjo1QG6qFsXvhAopblShGsVqMst1SZLyMzKFUvrvs1OQQDUBkhd7b2D3KRFY5uirhpni9IQbNbCzZ9wsxZutsJDlB5Ed9v_DV1sQgUA7ANaRsGaYr8LQYjw |
| CODEN | ITNNAL |
| CitedBy_id | crossref_primary_10_1007_s11633_022_1341_4 crossref_primary_10_3390_s25010019 crossref_primary_10_1051_sands_2024003 crossref_primary_10_1109_TCC_2024_3452696 crossref_primary_10_1016_j_jnca_2025_104104 crossref_primary_10_1145_3670854 crossref_primary_10_1109_ACCESS_2025_3535085 crossref_primary_10_1109_ACCESS_2025_3547627 crossref_primary_10_1007_s11704_023_3282_7 crossref_primary_10_1109_TKDE_2023_3341808 crossref_primary_10_1007_s40747_024_01636_4 crossref_primary_10_1109_TSUSC_2024_3403427 crossref_primary_10_1109_TIA_2024_3462668 crossref_primary_10_1109_TKDE_2023_3271851 crossref_primary_10_3390_su17052210 crossref_primary_10_1186_s13677_024_00721_w crossref_primary_10_1016_j_neunet_2025_107345 crossref_primary_10_1016_j_neunet_2024_106772 crossref_primary_10_3390_app13159007 crossref_primary_10_1109_LWC_2022_3220956 crossref_primary_10_1109_TCOMM_2024_3381671 crossref_primary_10_1109_TNNLS_2024_3370297 crossref_primary_10_1145_3725527 crossref_primary_10_1109_JIOT_2024_3357779 crossref_primary_10_1051_sands_2024014 crossref_primary_10_1007_s11227_024_06476_0 crossref_primary_10_1109_MVT_2024_3451191 crossref_primary_10_1109_TCE_2024_3385440 crossref_primary_10_1109_JIOT_2023_3299947 crossref_primary_10_1088_1361_6501_ad69b5 crossref_primary_10_1109_TII_2024_3417297 crossref_primary_10_3934_mbe_2023475 crossref_primary_10_1109_TNNLS_2024_3387757 crossref_primary_10_1109_TSG_2024_3415504 crossref_primary_10_1109_TFUZZ_2023_3335361 crossref_primary_10_1109_TDSC_2024_3419211 crossref_primary_10_1109_TKDE_2024_3390041 crossref_primary_10_3390_s23167235 crossref_primary_10_1109_ACCESS_2024_3369915 crossref_primary_10_1002_tee_24049 crossref_primary_10_1109_TAI_2023_3297090 crossref_primary_10_34133_icomputing_0089 crossref_primary_10_3390_fi16030082 crossref_primary_10_1007_s10916_023_01994_5 crossref_primary_10_1109_TNNLS_2024_3417452 crossref_primary_10_1109_ACCESS_2024_3359992 crossref_primary_10_1109_TMC_2024_3507286 crossref_primary_10_1016_j_ject_2024_12_003 crossref_primary_10_1109_TII_2022_3223234 crossref_primary_10_1109_TVT_2024_3447569 crossref_primary_10_1038_s41598_023_47078_9 crossref_primary_10_1109_JIOT_2024_3391342 crossref_primary_10_1016_j_comnet_2024_110822 crossref_primary_10_1109_TVT_2024_3499349 crossref_primary_10_1038_s41746_024_01272_9 crossref_primary_10_1109_TNSM_2023_3263831 crossref_primary_10_1016_j_future_2024_04_026 crossref_primary_10_1016_j_csbj_2024_10_037 crossref_primary_10_1093_ijlct_ctae283 crossref_primary_10_1109_TMC_2024_3396218 crossref_primary_10_1109_ACCESS_2024_3422211 crossref_primary_10_1109_JIOT_2024_3448626 crossref_primary_10_1007_s00530_024_01422_9 crossref_primary_10_3390_bs15010027 crossref_primary_10_1007_s10489_022_04065_3 crossref_primary_10_1109_JIOT_2024_3413780 crossref_primary_10_1109_MCOM_001_2300272 crossref_primary_10_1016_j_knosys_2024_112276 crossref_primary_10_1016_j_eswa_2024_124742 crossref_primary_10_33012_navi_688 crossref_primary_10_1145_3558005 crossref_primary_10_1109_TSUSC_2023_3341836 crossref_primary_10_1109_ACCESS_2023_3299443 crossref_primary_10_1109_JIOT_2024_3385479 crossref_primary_10_1109_TMC_2024_3449129 crossref_primary_10_1145_3690822 crossref_primary_10_1109_JRFID_2022_3218288 crossref_primary_10_1186_s13677_023_00535_2 crossref_primary_10_1109_TETC_2024_3471458 crossref_primary_10_3390_app14020586 crossref_primary_10_1007_s00521_024_09803_x crossref_primary_10_1039_D4EW00685B crossref_primary_10_1109_JSTSP_2024_3497660 crossref_primary_10_1109_ACCESS_2024_3413069 crossref_primary_10_1016_j_knosys_2023_110741 crossref_primary_10_3390_fi17010018 crossref_primary_10_1109_TMC_2024_3361876 crossref_primary_10_1109_LWC_2024_3482318 crossref_primary_10_1109_TPAMI_2024_3470072 crossref_primary_10_1109_TWC_2023_3339824 crossref_primary_10_1016_j_neucom_2025_130013 crossref_primary_10_1145_3638252 crossref_primary_10_1109_TMC_2024_3464512 crossref_primary_10_1109_JBHI_2024_3428512 crossref_primary_10_1109_TSIPN_2023_3325963 crossref_primary_10_1007_s10586_024_04714_x crossref_primary_10_1007_s40974_024_00323_x crossref_primary_10_1109_TMI_2024_3483221 crossref_primary_10_1145_3625558 crossref_primary_10_1109_TCE_2024_3378159 crossref_primary_10_1007_s00607_024_01405_8 crossref_primary_10_1007_s11063_023_11264_7 crossref_primary_10_1016_j_inffus_2024_102834 crossref_primary_10_1186_s13636_023_00299_2 crossref_primary_10_1109_JAS_2024_124215 crossref_primary_10_1109_TNNLS_2024_3394252 crossref_primary_10_1038_s41598_024_80048_3 crossref_primary_10_1109_JIOT_2024_3433460 crossref_primary_10_1109_JIOT_2024_3403256 crossref_primary_10_1109_COMST_2024_3399612 crossref_primary_10_1109_JRFID_2024_3390142 crossref_primary_10_1016_j_future_2024_06_049 crossref_primary_10_1109_JIOT_2024_3362587 crossref_primary_10_1016_j_measurement_2024_116275 crossref_primary_10_1109_JIOT_2024_3435994 crossref_primary_10_1016_j_ins_2024_120825 crossref_primary_10_1109_TMC_2024_3483272 crossref_primary_10_3390_fi16050164 crossref_primary_10_1364_OL_530189 crossref_primary_10_3389_fdgth_2024_1495999 crossref_primary_10_1145_3708983 crossref_primary_10_1109_TMC_2024_3453657 crossref_primary_10_26599_BDMA_2024_9020035 crossref_primary_10_1109_JIOT_2022_3228727 crossref_primary_10_1109_JSAC_2023_3345431 crossref_primary_10_1287_ijds_2024_0029 crossref_primary_10_1145_3678182 crossref_primary_10_1109_JSTSP_2022_3231527 crossref_primary_10_3390_app132312962 crossref_primary_10_3390_electronics14030410 crossref_primary_10_1109_ACCESS_2024_3349691 crossref_primary_10_1109_ACCESS_2024_3357514 crossref_primary_10_1109_TCCN_2024_3394889 crossref_primary_10_1109_TMC_2024_3466227 crossref_primary_10_1109_TNSM_2023_3278023 crossref_primary_10_1145_3706058 crossref_primary_10_1007_s11063_023_11420_z crossref_primary_10_3390_fi15120403 crossref_primary_10_1016_j_ins_2024_120760 crossref_primary_10_1109_TMLCN_2025_3528901 crossref_primary_10_1007_s42979_024_03137_0 crossref_primary_10_1371_journal_pdig_0000117 crossref_primary_10_1109_TMC_2024_3487294 crossref_primary_10_1109_TSC_2024_3436695 crossref_primary_10_3390_jsan14010009 crossref_primary_10_1109_OJCOMS_2024_3458088 crossref_primary_10_1016_j_bspc_2024_106068 crossref_primary_10_1080_24725854_2022_2157912 crossref_primary_10_1016_j_enbuild_2024_114176 crossref_primary_10_1109_TMC_2024_3509852 crossref_primary_10_3390_app142210547 crossref_primary_10_3390_s23156986 crossref_primary_10_1109_TPDS_2023_3294688 crossref_primary_10_1109_TII_2024_3452229 crossref_primary_10_1109_TBDATA_2022_3191439 crossref_primary_10_1007_s13042_022_01647_y crossref_primary_10_1016_j_compchemeng_2024_108749 crossref_primary_10_1007_s40012_023_00382_1 crossref_primary_10_1109_TIFS_2025_3531143 crossref_primary_10_1109_TETCI_2023_3251404 crossref_primary_10_1109_TKDE_2024_3352628 crossref_primary_10_1109_TGRS_2024_3370584 crossref_primary_10_1109_TMC_2024_3427636 crossref_primary_10_1007_s00530_025_01719_3 crossref_primary_10_1109_JIOT_2024_3443467 crossref_primary_10_1007_s11227_024_06529_4 crossref_primary_10_1145_3659205 crossref_primary_10_3390_en16176377 crossref_primary_10_1109_TMC_2024_3374706 crossref_primary_10_1016_j_dt_2024_12_024 crossref_primary_10_1109_TETC_2024_3390811 crossref_primary_10_1088_2632_2153_ada0a6 crossref_primary_10_1016_j_neunet_2024_106230 crossref_primary_10_1109_TII_2024_3380742 crossref_primary_10_1145_3656165 crossref_primary_10_1109_JRFID_2022_3209657 crossref_primary_10_1109_COMST_2022_3221119 crossref_primary_10_1109_JSTSP_2023_3343626 crossref_primary_10_1007_s10462_023_10417_3 crossref_primary_10_1007_s11704_024_40065_x crossref_primary_10_1016_j_sasc_2025_200212 crossref_primary_10_1016_j_isci_2024_110943 crossref_primary_10_3390_math13061004 crossref_primary_10_3390_s24010088 crossref_primary_10_3390_electronics13173538 crossref_primary_10_1109_TCC_2024_3482865 crossref_primary_10_1016_j_patter_2023_100913 crossref_primary_10_3390_network5010001 crossref_primary_10_1109_TIFS_2025_3539087 crossref_primary_10_1109_TC_2024_3353455 crossref_primary_10_2197_ipsjjip_32_1033 crossref_primary_10_1109_TPDS_2025_3539738 crossref_primary_10_1145_3704633 crossref_primary_10_3390_electronics13030527 crossref_primary_10_1109_ACCESS_2025_3532853 crossref_primary_10_1109_TCOMM_2024_3396748 crossref_primary_10_1109_ACCESS_2024_3508030 crossref_primary_10_1109_TII_2024_3393492 crossref_primary_10_1109_TSP_2024_3514802 crossref_primary_10_1109_TPDS_2022_3225185 crossref_primary_10_1007_s10462_023_10563_8 crossref_primary_10_1016_j_jprocont_2023_103038 crossref_primary_10_1016_j_future_2024_107594 crossref_primary_10_1109_JIOT_2024_3420696 crossref_primary_10_1109_JIOT_2023_3279273 crossref_primary_10_5753_jisa_2024_3826 crossref_primary_10_1016_j_displa_2023_102504 crossref_primary_10_1109_TIM_2023_3341116 crossref_primary_10_1007_s12194_024_00827_5 crossref_primary_10_1109_TPDS_2024_3411815 crossref_primary_10_1145_3643560 crossref_primary_10_1016_j_iot_2024_101318 crossref_primary_10_1109_TMI_2023_3234450 crossref_primary_10_1109_TSUSC_2023_3279111 crossref_primary_10_1016_j_eswa_2024_125336 crossref_primary_10_3390_electronics13091772 crossref_primary_10_1109_TIFS_2024_3416042 crossref_primary_10_1109_TNNLS_2024_3349400 crossref_primary_10_1145_3697836 crossref_primary_10_1016_j_segan_2024_101537 crossref_primary_10_1016_j_media_2024_103121 crossref_primary_10_1016_j_apenergy_2024_123016 crossref_primary_10_1007_s10489_023_04753_8 crossref_primary_10_1038_s41598_024_73863_1 crossref_primary_10_26634_jfet_19_4_20913 crossref_primary_10_1145_3649316 crossref_primary_10_3390_app142412024 crossref_primary_10_1109_JIOT_2024_3407584 crossref_primary_10_1145_3560816 crossref_primary_10_1016_j_ogla_2024_08_004 crossref_primary_10_1109_ACCESS_2024_3514972 crossref_primary_10_1109_TNNLS_2024_3360429 crossref_primary_10_1007_s10723_025_09796_4 crossref_primary_10_1109_JIOT_2022_3233599 crossref_primary_10_1145_3725221 crossref_primary_10_1109_COMST_2024_3393230 crossref_primary_10_1007_s11432_024_4254_5 crossref_primary_10_1007_s12145_024_01438_9 crossref_primary_10_1049_blc2_12054 crossref_primary_10_1109_TMC_2024_3437468 |
| Cites_doi | 10.1109/ICIP40778.2020.9190968 10.1609/aaai.v30i1.10306 10.1038/s41598-020-69250-1 10.1038/s41591-021-01506-3 10.1109/MIS.2020.2988604 10.1073/pnas.1611835114 10.1038/s41586-021-03583-3 10.1109/CVPR42600.2020.00756 10.1109/CVPR46437.2021.01057 10.1145/3387107 10.1109/IJCNN.2008.4633969 10.1109/NCA51143.2020.9306745 10.1007/978-3-030-32813-9_3 10.1016/j.jnca.2018.05.003 10.1016/j.future.2020.10.007 10.1109/INFOCOM41043.2020.9155494 10.1109/IJCNN52387.2021.9533876 10.1038/s42256-020-0186-1 10.1109/TNNLS.2019.2953131 10.1109/TPAMI.2021.3057446 10.1007/s40747-020-00247-z 10.1109/TNNLS.2022.3216981 10.1145/3461702.3462533 10.1145/3510540 10.1145/3369583.3392686 10.1109/5.726791 10.1016/j.inffus.2019.12.012 10.1145/3457607 10.1109/TNNLS.2020.3015958 10.1109/OJCS.2020.2993259 10.1109/TMC.2020.3045266 10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00042 10.1109/TETC.2021.3063517 10.1109/TPDS.2020.3009406 10.1609/aaai.v36i8.20825 10.1109/COMST.2020.2986024 10.1109/MSP.2020.2975749 10.48550/arXiv.1503.02531 10.1007/978-3-319-57959-7 10.1109/TKDE.2009.191 10.1109/ICCV.2015.425 10.1109/TPDS.2020.2996273 10.1609/aaai.v32i1.11651 10.1007/978-3-030-58607-2_5 10.18653/v1/2020.emnlp-main.165 10.1109/TKDE.2018.2876857 10.1109/ACCESS.2018.2870052 10.1007/978-981-16-1160-5_14 10.1613/jair.953 10.1109/IJCNN48605.2020.9207469 10.3390/e22030314 10.1109/IJCNN.2017.7966217 10.1145/3298981 10.1109/TPAMI.2021.3079209 10.1609/aaai.v35i9.16960 10.1109/SRDS51746.2020.00017 10.1109/BigData55660.2022.10020232 10.1561/2200000083 10.1007/978-3-030-62579-5_6 10.1145/3290605.3300830 10.1109/TNSE.2020.2996612 10.23919/EUSIPCO54536.2021.9616052 10.1016/j.jbi.2019.103291 10.1109/CVPR42600.2020.00206 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| DOI | 10.1109/TNNLS.2022.3160699 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Chemoreception Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Chemoreception Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Electronics & Communications Abstracts Ceramic Abstracts Neurosciences Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed Materials Research Database |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2162-2388 |
| EndPage | 9603 |
| ExternalDocumentID | 35344498 10_1109_TNNLS_2022_3160699 9743558 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: Shandong Provincial Key Research and Development Program through the Major Scientific and Technological Innovation Project grantid: 2021CXGC010108 – fundername: Nanyang Assistant Professorship; – fundername: AI Singapore Program, National Research Foundation, Singapore grantid: AISG2-RP-2020-019 funderid: 10.13039/501100001381 – fundername: RIE 2020 Advanced Manufacturing and Engineering Programmatic Fund, Singapore grantid: A20G8b0102 – fundername: Hong Kong RGC TRS grantid: T41-603/20-R – fundername: Nanyang Technological University, Singapore funderid: 10.13039/501100001475 – fundername: Joint SDU-NTU Centre for Artificial Intelligence Research grantid: NSC-2019-011 – fundername: Alibaba Group through the Alibaba Innovative Research Program and the Alibaba-NTU Singapore Joint Research Institute grantid: Alibaba-NTU-AIR2019B1 – fundername: National Key Research and Development Program of China grantid: 2021YFF0900800; 2018AAA0101100 funderid: 10.13039/501100012166 – fundername: SDNSFC grantid: ZR2019LZH008 |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION RIG NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| ID | FETCH-LOGICAL-c266t-af6a60355675b474ed02b3886978bb4c1558b7f97d333f10ab87fcc0821abe7d3 |
| IEDL.DBID | RIE |
| ISSN | 2162-237X 2162-2388 |
| IngestDate | Thu Jul 10 18:28:33 EDT 2025 Sun Jun 29 12:34:07 EDT 2025 Thu Apr 03 07:09:35 EDT 2025 Tue Jul 01 00:27:45 EDT 2025 Thu Apr 24 22:54:43 EDT 2025 Wed Aug 27 02:07:45 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 12 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c266t-af6a60355675b474ed02b3886978bb4c1558b7f97d333f10ab87fcc0821abe7d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0001-6893-8650 0000-0001-5059-8360 0000-0003-0084-3473 0000-0002-8262-8883 |
| PMID | 35344498 |
| PQID | 2895881598 |
| PQPubID | 85436 |
| PageCount | 17 |
| ParticipantIDs | crossref_citationtrail_10_1109_TNNLS_2022_3160699 crossref_primary_10_1109_TNNLS_2022_3160699 pubmed_primary_35344498 ieee_primary_9743558 proquest_journals_2895881598 proquest_miscellaneous_2644962366 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-12-01 |
| PublicationDateYYYYMMDD | 2023-12-01 |
| PublicationDate_xml | – month: 12 year: 2023 text: 2023-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Piscataway |
| PublicationTitle | IEEE transaction on neural networks and learning systems |
| PublicationTitleAbbrev | TNNLS |
| PublicationTitleAlternate | IEEE Trans Neural Netw Learn Syst |
| PublicationYear | 2023 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | Lin (ref97) Vepakomma (ref50) 2018 ref53 Khodak (ref40); 32 ref52 ref54 He (ref57); 33 Bistritz (ref58); 33 ref51 Li (ref88) ref45 ref41 ref44 ref43 ref49 ref8 ref7 ref4 ref3 ref6 ref5 Shoham (ref62) 2019 ref100 ref101 Dinh (ref39); 33 Li (ref13) Harry Hsu (ref86) 2019 Hanzely (ref63) 2020 ref31 ref30 Fallah (ref38) Tonekaboni (ref111) ref33 ref32 Fallah (ref37); 33 Li (ref42) 2019 Nichol (ref35) 2018 Corinzia (ref60) 2019 Luo (ref82) 2019 ref24 ref23 ref26 ref25 McMahan (ref9) ref28 Wang (ref92) ref27 Mansour (ref17) 2020 Li (ref106) Pu Liang (ref48) 2020 Li (ref29); 2 ref15 ref14 ref96 ref11 ref99 ref10 ref98 ref16 ref19 ref18 Diao (ref65) Arivazhagan (ref46) 2019 ref93 ref95 ref94 ref91 ref90 Bui (ref47) 2019 Ghosh (ref68); 33 Caldas (ref79) 2018 ref81 ref84 ref83 He (ref78) 2021 ref80 ref108 Xie (ref72) 2020 Wang (ref87) 2019 ref109 ref75 ref104 ref74 ref77 ref102 ref76 ref103 ref2 ref1 Zhang (ref107) 2020 Krizhevsky (ref85) 2009 Kubat (ref20) Smith (ref59); 30 Divi (ref89) 2021 Jeong (ref22) 2018 Zhao (ref21) 2018 ref70 ref112 ref73 ref110 Finn (ref34) Vassilvitskii (ref71) ref67 Lin (ref56); 33 ref69 Jiang (ref36) 2019 ref66 Zhu (ref55) Deng (ref64) 2020 Mohri (ref105) Karimireddy (ref12) ref61 |
| References_xml | – ident: ref30 doi: 10.1109/ICIP40778.2020.9190968 – year: 2019 ident: ref62 article-title: Overcoming forgetting in federated learning on non-IID data publication-title: arXiv:1910.07796 – ident: ref45 doi: 10.1609/aaai.v30i1.10306 – ident: ref3 doi: 10.1038/s41598-020-69250-1 – ident: ref4 doi: 10.1038/s41591-021-01506-3 – ident: ref43 doi: 10.1109/MIS.2020.2988604 – ident: ref31 doi: 10.1073/pnas.1611835114 – ident: ref2 doi: 10.1038/s41586-021-03583-3 – ident: ref73 doi: 10.1109/CVPR42600.2020.00756 – volume: 2 start-page: 429 volume-title: Proc. Mach. Learn. Syst. ident: ref29 article-title: Federated optimization in heterogeneous networks – year: 2020 ident: ref63 article-title: Federated learning of a mixture of global and local models publication-title: arXiv:2002.05516 – year: 2018 ident: ref35 article-title: On first-order meta-learning algorithms publication-title: arXiv:1803.02999 – ident: ref32 doi: 10.1109/CVPR46437.2021.01057 – ident: ref6 doi: 10.1145/3387107 – year: 2020 ident: ref107 article-title: Hierarchically fair federated learning publication-title: arXiv:2004.10386 – ident: ref19 doi: 10.1109/IJCNN.2008.4633969 – ident: ref10 doi: 10.1109/NCA51143.2020.9306745 – ident: ref76 doi: 10.1007/978-3-030-32813-9_3 – ident: ref49 doi: 10.1016/j.jnca.2018.05.003 – start-page: 1273 volume-title: Proc. AISTATS ident: ref9 article-title: Communication-efficient learning of deep networks from decentralized data – year: 2020 ident: ref48 article-title: Think locally, act globally: Federated learning with local and global representations publication-title: arXiv:2001.01523 – ident: ref15 doi: 10.1016/j.future.2020.10.007 – year: 2019 ident: ref60 article-title: Variational federated multi-task learning publication-title: arXiv:1906.06268 – ident: ref25 doi: 10.1109/INFOCOM41043.2020.9155494 – ident: ref28 doi: 10.1109/IJCNN52387.2021.9533876 – volume: 33 start-page: 3557 volume-title: Proc. NIPS ident: ref37 article-title: Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach – ident: ref1 doi: 10.1038/s42256-020-0186-1 – volume: 30 start-page: 4427 volume-title: Proc. Adv. Neural Inf. Process. Syst. (NIPS) ident: ref59 article-title: Federated multi-task learning – year: 2020 ident: ref72 article-title: Multi-center federated learning publication-title: arXiv:2005.01026 – ident: ref98 doi: 10.1109/TNNLS.2019.2953131 – year: 2019 ident: ref36 article-title: Improving federated learning personalization via model agnostic meta learning publication-title: arXiv:1909.12488 – year: 2019 ident: ref87 article-title: Federated evaluation of on-device personalization publication-title: arXiv:1910.10252 – year: 2020 ident: ref64 article-title: Adaptive personalized federated learning publication-title: arXiv:2003.13461 – ident: ref96 doi: 10.1109/TPAMI.2021.3057446 – ident: ref93 doi: 10.1007/s40747-020-00247-z – start-page: 1 volume-title: Proc. ICLR ident: ref65 article-title: Heterofl: Computation and communication efficient federated learning for heterogeneous clients – ident: ref16 doi: 10.1109/TNNLS.2022.3216981 – start-page: 179 volume-title: Proc. ICML ident: ref20 article-title: Addressing the curse of imbalanced training sets: One-sided selection – volume: 33 start-page: 2351 volume-title: Proc. NIPS ident: ref56 article-title: Ensemble distillation for robust model fusion in federated learning – ident: ref112 doi: 10.1145/3461702.3462533 – ident: ref77 doi: 10.1145/3510540 – year: 2019 ident: ref86 article-title: Measuring the effects of non-identical data distribution for federated visual classification publication-title: arXiv:1909.06335 – ident: ref27 doi: 10.1145/3369583.3392686 – ident: ref84 doi: 10.1109/5.726791 – ident: ref110 doi: 10.1016/j.inffus.2019.12.012 – start-page: 1 volume-title: Proc. ICLR ident: ref97 article-title: Deep gradient compression: Reducing the communication bandwidth for distributed training – year: 2018 ident: ref21 article-title: Federated learning with non-IID data publication-title: arXiv:1806.00582 – ident: ref103 doi: 10.1145/3457607 – volume: 33 start-page: 19586 volume-title: Proc. NIPS ident: ref68 article-title: An efficient framework for clustered federated learning – ident: ref66 doi: 10.1109/TNNLS.2020.3015958 – ident: ref94 doi: 10.1109/OJCS.2020.2993259 – year: 2018 ident: ref79 article-title: LEAF: A benchmark for federated settings publication-title: arXiv:1812.01097 – year: 2019 ident: ref42 article-title: FedMD: Heterogenous federated learning via model distillation publication-title: arXiv:1910.03581 – ident: ref24 doi: 10.1109/TMC.2020.3045266 – ident: ref70 doi: 10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00042 – volume: 32 start-page: 5917 volume-title: Proc. NIPS ident: ref40 article-title: Adaptive gradient-based meta-learning methods – ident: ref102 doi: 10.1109/TETC.2021.3063517 – start-page: 359 volume-title: Proc. MLHC ident: ref111 article-title: What clinicians want: Contextualizing explainable machine learning for clinical end use – ident: ref23 doi: 10.1109/TPDS.2020.3009406 – ident: ref51 doi: 10.1609/aaai.v36i8.20825 – ident: ref11 doi: 10.1109/COMST.2020.2986024 – ident: ref14 doi: 10.1109/MSP.2020.2975749 – volume: 33 start-page: 21394 volume-title: Proc. Adv. Neural Inf. Process. Syst. (NIPS) ident: ref39 article-title: Personalized federated learning with Moreau envelopes – ident: ref54 doi: 10.48550/arXiv.1503.02531 – ident: ref5 doi: 10.1007/978-3-319-57959-7 – ident: ref41 doi: 10.1109/TKDE.2009.191 – ident: ref81 doi: 10.1109/ICCV.2015.425 – ident: ref108 doi: 10.1109/TPDS.2020.2996273 – ident: ref95 doi: 10.1609/aaai.v32i1.11651 – start-page: 1082 volume-title: Proc. AISTATS ident: ref38 article-title: On the convergence theory of gradient-based model-agnostic meta-learning algorithms – ident: ref83 doi: 10.1007/978-3-030-58607-2_5 – ident: ref90 doi: 10.18653/v1/2020.emnlp-main.165 – ident: ref99 doi: 10.1109/TKDE.2018.2876857 – year: 2020 ident: ref17 article-title: Three approaches for personalization with applications to federated learning publication-title: arXiv:2002.10619 – start-page: 1 volume-title: Proc. ICLR ident: ref92 article-title: Federated learning with matched averaging – ident: ref109 doi: 10.1109/ACCESS.2018.2870052 – start-page: 1126 volume-title: Proc. ICML ident: ref34 article-title: Model-agnostic meta-learning for fast adaptation of deep networks – ident: ref75 doi: 10.1007/978-981-16-1160-5_14 – year: 2018 ident: ref22 article-title: Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data publication-title: arXiv:1811.11479 – year: 2019 ident: ref47 article-title: Federated user representation learning publication-title: arXiv:1909.12535 – ident: ref18 doi: 10.1613/jair.953 – volume-title: MIT and NYU year: 2009 ident: ref85 article-title: Learning multiple layers of features from tiny images – ident: ref67 doi: 10.1109/IJCNN48605.2020.9207469 – year: 2019 ident: ref46 article-title: Federated learning with personalization layers publication-title: arXiv:1912.00818 – start-page: 1 volume-title: Proc. ICLR ident: ref106 article-title: Fair resource allocation in federated learning – ident: ref91 doi: 10.3390/e22030314 – ident: ref80 doi: 10.1109/IJCNN.2017.7966217 – year: 2021 ident: ref78 article-title: FedGraphNN: A federated learning system and benchmark for graph neural networks publication-title: arXiv:2104.07145 – ident: ref7 doi: 10.1145/3298981 – ident: ref33 doi: 10.1109/TPAMI.2021.3079209 – ident: ref61 doi: 10.1609/aaai.v35i9.16960 – volume-title: ICML ident: ref55 article-title: Data-free knowledge distillation for heterogeneous federated learning – ident: ref52 doi: 10.1109/SRDS51746.2020.00017 – ident: ref53 doi: 10.1145/3298981 – ident: ref101 doi: 10.1109/BigData55660.2022.10020232 – ident: ref8 doi: 10.1561/2200000083 – start-page: 5132 volume-title: Proc. ICML ident: ref12 article-title: SCAFFOLD: Stochastic controlled averaging for federated learning – start-page: 1 volume-title: Proc. ICLR ident: ref13 article-title: On the convergence of FedAvg on non-IID data – year: 2018 ident: ref50 article-title: Split learning for health: Distributed deep learning without sharing raw patient data publication-title: arXiv:1812.00564 – start-page: 4615 volume-title: Proc. ICML ident: ref105 article-title: Agnostic federated learning – ident: ref100 doi: 10.1007/978-3-030-62579-5_6 – ident: ref104 doi: 10.1145/3290605.3300830 – ident: ref44 doi: 10.1109/TNSE.2020.2996612 – ident: ref26 doi: 10.23919/EUSIPCO54536.2021.9616052 – year: 2019 ident: ref82 article-title: Real-world image datasets for federated learning publication-title: arXiv:1910.11089 – start-page: 6357 volume-title: Proc. ICML ident: ref88 article-title: Ditto: Fair and robust federated learning through personalization – volume: 33 start-page: 14068 volume-title: Proc. NIPS ident: ref57 article-title: Group knowledge transfer: Federated learning of large cnns at the edge – year: 2021 ident: ref89 article-title: New metrics to evaluate the performance and fairness of personalized federated learning publication-title: arXiv:2107.13173 – start-page: 1027 volume-title: Proc. ACM-SIAM ident: ref71 article-title: K-means: The advantages of careful seeding – volume: 33 start-page: 22593 volume-title: Proc. NIPS ident: ref58 article-title: Distributed distillation for on-device learning – ident: ref69 doi: 10.1016/j.jbi.2019.103291 – ident: ref74 doi: 10.1109/CVPR42600.2020.00206 |
| SSID | ssj0000605649 |
| Score | 2.7540824 |
| Snippet | In parallel with the rapid adoption of artificial intelligence (AI) empowered by advances in AI research, there has been growing awareness and concerns of data... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 9587 |
| SubjectTerms | Adaptation models Architectural design Artificial intelligence Collaborative work Customization Data models Data privacy Edge computing Federated learning federated learning (FL) Machine learning non-IID data personalized FL (PFL) Privacy privacy preservation Servers statistical heterogeneity Taxonomy Training |
| Title | Towards Personalized Federated Learning |
| URI | https://ieeexplore.ieee.org/document/9743558 https://www.ncbi.nlm.nih.gov/pubmed/35344498 https://www.proquest.com/docview/2895881598 https://www.proquest.com/docview/2644962366 |
| Volume | 34 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3PS8MwFH7Mnbw4df6YTqkgeNBuaZKl6VHEMcQNwQ12K02belA6ce1lf70v6Q9QVLyVJm3TvIR8X_Le9wAujfh1EFDfjRRTLsc1x0WuIlwqZUpShATEJpuYzsRkwR-Wo2ULbppYGK21dT7TA3Npz_KTVVyYrbIhYl-jBr4FW0jcylitZj-FIC4XFu1ST1CXMn9Zx8iQYDifzR6fkQ1SiiQVMXtg1ELZiHHOA_llSbI5Vn6Hm3bZGXdgWje49DZ5HRS5GsSbb1qO__2jXdip8KdzWw6YPWjpbB86dW4Hp5rqXbiaW3_atfNUo_WNTpyxkZ5AdJo4lS7rywEsxvfzu4lbJVVwY1yLczdKRSQIfhSZguI-1wmhikkp0ERK8RjxhVR-GvgJYyz1SKSkn8YxIgUvUhrvHkI7W2X6GBwvZjzxPGViXTlRQsoE6VqSypFvNHVoD7y6X8O4Uhw3iS_eQss8SBBas4TGLGFllh5cN8-8l3obf9bumj5talbd2YN-bb6wmpLrEJklNhTRGxZfNMU4mcwJSZTpVYF1EB0GCAiF6MFRafbm3fVoOfn5m6ewbTLRl54ufWjnH4U-Q7ySq3M7UD8BpAbfdg |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NT8IwFH9BPOhFVPxAUWdi4kEHXVu67miMBBWIiZBwW9at86ABI3Dhr_e1-0g0arwta7d-vDbv99r3fg_gwpBfBwH13Ugx5XLUOS7aKsKlUqYkRUhAbLKJwVD0xvxh0plU4LqMhdFaW-cz3TKP9i4_mcVLc1TWRuxr2MDXYB31fodm0VrliQpBZC4s3qWeoC5l_qSIkiFBezQc9p_RHqQUzVRE7YHhC2UdxjkP5BelZLOs_A44reLp1mBQdDnzN3ltLReqFa--sTn-d0zbsJUjUOcmWzI7UNHTXagV2R2cfLPX4XJkPWrnzlOB11c6cbqGfALxaeLkzKwvezDu3o1ue26eVsGNURsv3CgVkSDYKNoKivtcJ4QqJqVAISnFY0QYUvlp4CeMsdQjkZJ-GseIFbxIaXy7D9XpbKoPwfFixhPPUybalRMlpEzQYEtS2fENqw5tgFfMaxjnnOMm9cVbaG0PEoRWLKERS5iLpQFX5TfvGePGn7XrZk7Lmvl0NqBZiC_MN-U8RNsSO4r4DYvPy2LcTuaOJJrq2RLrID4MEBIK0YCDTOzlv4vVcvRzm2ew0RsN-mH_fvh4DJsmL33m99KE6uJjqU8QvSzUqV20n3y_4sA |
| 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=Towards+Personalized+Federated+Learning&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Tan%2C+Alysa+Ziying&rft.au=Yu%2C+Han&rft.au=Cui%2C+Lizhen&rft.au=Yang%2C+Qiang&rft.date=2023-12-01&rft.issn=2162-2388&rft.eissn=2162-2388&rft.volume=34&rft.issue=12&rft.spage=9587&rft_id=info:doi/10.1109%2FTNNLS.2022.3160699&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon |