{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:06:26Z","timestamp":1770739586833,"version":"3.49.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Project of Key Research and Development Program of Shandong Province","award":["2024CXGC010113"],"award-info":[{"award-number":["2024CXGC010113"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472253"],"award-info":[{"award-number":["62472253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20273"],"award-info":[{"award-number":["U23A20273"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Taishan Scholars Program","doi-asserted-by":"publisher","award":["tsqn202408025"],"award-info":[{"award-number":["tsqn202408025"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3654864","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:49:14Z","timestamp":1768510154000},"page":"2911-2926","source":"Crossref","is-referenced-by-count":0,"title":["ROSS: RObust Decentralized Stochastic Learning Based on Shapley Values"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9448-8614","authenticated-orcid":false,"given":"Lina","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"given":"Yunsheng","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3746-2132","authenticated-orcid":false,"given":"Feng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0217-6507","authenticated-orcid":false,"given":"Lingjie","family":"Duan","sequence":"additional","affiliation":[{"name":"Internet of Things Thrust and the Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th AISTATS","author":"McMahan"},{"key":"ref2","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. 31st NIPS","volume":"30","author":"Lian"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.132.2200530"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10894"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412599"},{"key":"ref9","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. 38th ICML","author":"Li"},{"key":"ref10","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","volume-title":"Proc. 36th ICML","author":"Tang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3108197"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3376548"},{"key":"ref14","first-page":"28004","article-title":"RelaySum for decentralized deep learning on heterogeneous data","volume-title":"Proc. 34th NIPS","volume":"34","author":"Vogels"},{"key":"ref15","first-page":"36132","article-title":"Epidemic learning: Boosting decentralized learning with randomized communication","volume-title":"Proc. 37th NeurIPS","author":"Vos"},{"key":"ref16","first-page":"6654","article-title":"Quasi-global momentum: Accelerating decentralized deep learning on heterogeneous data","volume-title":"Proc. 38th ICML","volume":"139","author":"Lin"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3492866.3549723"},{"key":"ref19","article-title":"Momentum tracking: Momentum acceleration for decentralized deep learning on heterogeneous data","volume":"2023","author":"Takezawa","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref20","first-page":"48939","article-title":"Global update tracking: A decentralized learning algorithm for heterogeneous data","volume-title":"Proc. 37th NIPS","author":"Aketi"},{"key":"ref21","first-page":"3036","article-title":"Cross-gradient aggregation for decentralized learning from non-IID data","volume-title":"Proc. 38th ICML","author":"Esfandiari"},{"key":"ref22","article-title":"Neighborhood gradient mean: An efficient decentralized learning method for non-IID data distributions","volume":"2023","author":"Aketi","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.874516"},{"key":"ref24","first-page":"5904","article-title":"Collaborative deep learning in fixed topology networks","volume-title":"Proc. 31st NIPS","author":"Jiang"},{"key":"ref25","first-page":"344","article-title":"Stochastic gradient push for distributed deep learning","volume-title":"Proc. 36th ICML","author":"Assran"},{"key":"ref26","article-title":"Asynchronous decentralized SGD with quantized and local updates","author":"Nadiradze","year":"2019","journal-title":"arXiv:1910.12308"},{"key":"ref27","first-page":"5381","article-title":"A unified theory of decentralized SGD with changing topology and local updates","volume-title":"Proc. 37th ICML","volume":"1","author":"Koloskova"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414564"},{"key":"ref29","first-page":"13975","article-title":"Exponential graph is provably efficient for decentralized deep training","volume-title":"Proc. 34th NIPS","author":"Ying"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00302"},{"key":"ref31","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine learning","volume-title":"Proc. 37th ICML","volume":"1","author":"Hsieh"},{"key":"ref32","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. 35th ICML","author":"Yin"},{"key":"ref33","first-page":"4855","article-title":"D2: Decentralized training over decentralized data","volume-title":"Proc. 35th ICML","author":"Tang"},{"key":"ref34","first-page":"25044","article-title":"Collaborative learning in the jungle (decentralized, Byzantine, heterogeneous, asynchronous and nonconvex Learning)","volume-title":"Proc. 35th NIPS","volume":"34","author":"El-Mhamdi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670307"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00228"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3501811"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599500"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17093"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539328"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881970-018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF01753431"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3137321"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2008.04.004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.05.003"},{"key":"ref47","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. 36th ICML","author":"Yu"},{"issue":"213","key":"ref48","first-page":"1","article-title":"Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Yurochkin"},{"key":"ref50","first-page":"1565","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. 33rd NIPS","author":"Cao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_24"},{"key":"ref52","first-page":"8632","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. NeurIPS","volume":"32","author":"Baruch"},{"key":"ref53","first-page":"3252","article-title":"Error feedback fixes SignSGD and other gradient compression schemes","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Karimireddy"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796982"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3247798"},{"key":"ref56","first-page":"1605","article-title":"Local model poisoning attacks to Byzantine-robust federated learning","volume-title":"Proc. 29th USENIX Secur. Symp.","author":"Fang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3116976"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11355683.pdf?arnumber=11355683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:04:06Z","timestamp":1770671046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11355683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3654864","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}