{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T05:50:16Z","timestamp":1775713816289,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFA1014002"],"award-info":[{"award-number":["2024YFA1014002"]}]},{"name":"NSF China","award":["62373388"],"award-info":[{"award-number":["62373388"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021B1515-020094"],"award-info":[{"award-number":["2021B1515-020094"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Mathematical Foundations for Artificial Intelligence","award":["2023B1212010001"],"award-info":[{"award-number":["2023B1212010001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3526989","type":"journal-article","created":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:18:59Z","timestamp":1736453939000},"page":"843-857","source":"Crossref","is-referenced-by-count":7,"title":["Generalization Error Matters in Decentralized Learning Under Byzantine Attacks"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5707-922X","authenticated-orcid":false,"given":"Haoxiang","family":"Ye","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-5964","authenticated-orcid":false,"given":"Qing","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, Guangdong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447366"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3292497"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3408631"},{"key":"ref5","first-page":"5331","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lian","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2022.3151242"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3184770"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3363887"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref11","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yin","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref13","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Blanchard","year":"2017"},{"key":"ref14","first-page":"5311","article-title":"Learning from history for Byzantine robust optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3340028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3300629"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2022.3188456"},{"key":"ref20","article-title":"Byzantine-robust decentralized learning via self-centered clipping","author":"He","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447047"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17173"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25894"},{"key":"ref24","first-page":"27479","article-title":"Topology-aware generalization of decentralized SGD","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu","year":"2022"},{"key":"ref25","first-page":"26215","article-title":"Improved stability and generalization guarantees of the decentralized SGD algorithm","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bars","year":"2024"},{"issue":"34","key":"ref26","first-page":"1","article-title":"Graph-dependent implicit regularisation for distributed stochastic subgradient descent","volume":"21","author":"Richards","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","first-page":"4917","article-title":"On generalization of decentralized learning with separable data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Taheri","year":"2023"},{"key":"ref28","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"Bousquet","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hardt","year":"2016"},{"key":"ref30","first-page":"4863","article-title":"Generalization guarantees via algorithm-dependent Rademacher complexity","volume-title":"Proc. Annu. Conf. Learn. Theory","author":"Sachs","year":"2023"},{"key":"ref31","first-page":"2935","article-title":"A PAC-Bayesian analysis of randomized learning with application to stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"London","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CAMSAP45676.2019.9022672"},{"key":"ref33","first-page":"2521","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2017"},{"key":"ref34","first-page":"2364","article-title":"Stability of SGD: Tightness analysis and improved bounds","volume-title":"Proc. 38th Conf. Uncertainty Artif. Intell.","author":"Zhang","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0015"},{"key":"ref36","first-page":"2635","article-title":"Learnability, stability and uniform convergence","volume":"11","author":"Shalev-Shwartz","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2025.3526989"},{"key":"ref38","article-title":"Stability and convergence trade-off of iterative optimization algorithms","author":"Chen","year":"2018"},{"key":"ref39","first-page":"19836","article-title":"Time-independent generalization bounds for SGLD in non-convex settings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Farghly","year":"2021"},{"key":"ref40","first-page":"1794","article-title":"Uniform-in-time Wasserstein stability bounds for (noisy) stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu","year":"2023"},{"key":"ref41","article-title":"Convex SGD: Generalization without early stopping","author":"Hendrickx","year":"2024"},{"key":"ref42","first-page":"8635","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baruch","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090952"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/10834510.pdf?arnumber=10834510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:50:00Z","timestamp":1740084600000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10834510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3526989","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}