{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:29:06Z","timestamp":1779906546993,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62501284"],"award-info":[{"award-number":["62501284"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30925010533"],"award-info":[{"award-number":["30925010533"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770940","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unveiling Byzantine-robust with Varied Batch Sizes across Different Clients in Federated Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9742-0637","authenticated-orcid":false,"given":"Yunxuan","family":"Li","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Nanjing University of Science & Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8883-1241","authenticated-orcid":false,"given":"Yuxin","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Nanjing University of Science & Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8956-7326","authenticated-orcid":false,"given":"Xinjian","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Nanjing University of Science & Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_3_2_2","series-title":"(ICML \u201920)","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Ajalloeian Ahmad","year":"2020","unstructured":"Ahmad Ajalloeian and Sebastian\u00a0U. Stich. 2020. Analysis of SGD with biased gradient estimators. In Proceedings of the 37th International Conference on Machine Learning(ICML \u201920)."},{"key":"e_1_3_3_3_3_2","series-title":"ICML \u201916","first-page":"699","volume-title":"Proceedings of the 33rd International Conference on Machine Learning","volume":"48","author":"Allen-Zhu Zeyuan","year":"2016","unstructured":"Zeyuan Allen-Zhu and Elad Hazan. 2016. Variance reduction for faster non-convex optimization. In Proceedings of the 33rd International Conference on Machine Learning(ICML \u201916, Vol.\u00a048). 699\u2013707."},{"key":"e_1_3_3_3_4_2","series-title":"(ICLR \u201925)","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Allouah Youssef","year":"2025","unstructured":"Youssef Allouah, Rachid Guerraoui, Nirupam Gupta, Ahmed Jellouli, Geovani Rizk, and John Stephan. 2025. Adaptive gradient clipping for robust federated learning. In Proceedings of the International Conference on Learning Representations(ICLR \u201925)."},{"key":"e_1_3_3_3_5_2","unstructured":"Peva Blanchard El\u00a0Mahdi\u00a0El Mhamdi Rachid Guerraoui and Julien Stainer. 2017. Machine learning with adversaries: Byzantine tolerant gradient descent. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"crossref","unstructured":"Yudong Chen Lili Su and Jiaming Xu. 2017. Distributed statistical machine learning in adversarial settings: Byzantine gradient descent. Proceedings of the ACM on Measurement and Analysis of Computing Systems 1 2 (2017) 1\u201325.","DOI":"10.1145\/3154503"},{"key":"e_1_3_3_3_7_2","series-title":"(NeurIPS \u201919)","first-page":"15210","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Cutkosky Ashok","year":"2019","unstructured":"Ashok Cutkosky and Francesco Orabona. 2019. Momentum-based variance reduction in nonconvex SGD. In Proceedings of the 32nd International Conference on Neural Information Processing Systems(NeurIPS \u201919). 15210\u201315219."},{"key":"e_1_3_3_3_8_2","series-title":"(ICML \u201918)","first-page":"1145","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Damaskinos Georgios","year":"2018","unstructured":"Georgios Damaskinos, Rachid Guerraoui, Rhicheek Patra, and Mahsa Taziki. 2018. Asynchronous Byzantine machine learning (the case of SGD). In Proceedings of the 35th International Conference on Machine Learning(ICML \u201918). PMLR, 1145\u20131154."},{"key":"e_1_3_3_3_9_2","unstructured":"Aaron Defazio Francis Bach and Simon Lacoste-Julien. 2014. SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives. Advances in Neural Information Processing Systems 27 (2014)."},{"key":"e_1_3_3_3_10_2","series-title":"(NeurIPS \u201918)","first-page":"687","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Fang Cong","year":"2018","unstructured":"Cong Fang, Chris\u00a0Junchi Li, Zhouchen Lin, and Tong Zhang. 2018. SPIDER: Near-optimal nonconvex optimization via stochastic path integrated differential estimator. In Proceedings of the 31st International Conference on Neural Information Processing Systems(NeurIPS \u201918). 687\u2013697."},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715491"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714728"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670307"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35305-5_3"},{"key":"e_1_3_3_3_15_2","unstructured":"Eduard Gorbunov Samuel Horv\u00e1th Peter Richt\u00e1rik and Gauthier Gidel. 2023. Variance reduction is an antidote to Byzantines: Better rates weaker assumptions and communication compression as a cherry on the top. International Conference on Learning Representations (2023)."},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0M. Gower Mark Schmid Francis Bach and Peter Richt\u00e1rik. 2020. Variance-reduced methods for machine learning. Proc. IEEE 108 11 (2020) 1968\u20131983.","DOI":"10.1109\/JPROC.2020.3028013"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Rachid Guerraoui Nirupam Gupta and Rafael Pinot. 2024. Byzantine machine learning: A primer. Comput. Surveys 56 7 (2024) 1\u201339.","DOI":"10.1145\/3616537"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Jinhui Hu Guo Chen Huaqing Li Xiaoyu Guo Liang Ran and Tingwen Huang. 2025. Prox-DBRO-VR: A unified analysis on Byzantine-resilient decentralized stochastic composite optimization with variance reduction and nonasymptotic convergence rates. IEEE Transactions on Systems Man and Cybernetics: Systems (2025) 1\u201314.","DOI":"10.1109\/TSMC.2025.3565568"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29146"},{"key":"e_1_3_3_3_20_2","unstructured":"Wei Jiang Sifan Yang Yibo Wang and Lijun Zhang. 2024. Adaptive variance reduction for stochastic optimization under weaker assumptions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.01959 (2024)."},{"key":"e_1_3_3_3_21_2","unstructured":"Rie Johnson and Tong Zhang. 2013. Accelerating stochastic gradient descent using predictive variance reduction. Advances in Neural Information Processing Systems 26 (2013)."},{"key":"e_1_3_3_3_22_2","series-title":"(ICML \u201921)","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Li Zhize","year":"2021","unstructured":"Zhize Li, Hongyan Bao, Xiangliang Zhang, and Peter Richt\u00e1rik. 2021. PAGE: A simple and optimal probabilistic gradient estimator for nonconvex optimization. In Proceedings of the 38th International Conference on Machine Learning(ICML \u201921)."},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Yunming Liao Yang Xu Hongli Xu Min Chen Lun Wang and Chunming Qiao. 2024. Asynchronous decentralized federated learning for heterogeneous devices. IEEE\/ACM Transactions on Networking (2024).","DOI":"10.1109\/TNET.2024.3424444"},{"key":"e_1_3_3_3_24_2","unstructured":"Xuezheng Liu Yipeng Zhou Di Wu Miao Hu Jessie\u00a0Hui Wang and Mohsen Guizani. 2024. FedDP-SA: Boosting differentially private federated learning via local dataset splitting. IEEE Internet of Things Journal (2024)."},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"crossref","unstructured":"Zhenguo Ma Yang Xu Hongli Xu Zeyu Meng Liusheng Huang and Yinxing Xue. 2023. Adaptive batch size for federated learning in resource-constrained edge computing. IEEE Transactions on Mobile Computing 22 1 (2023) 37\u201353.","DOI":"10.1109\/TMC.2021.3075291"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Yuyi Mao Xianghao Yu Kaibin Huang Ying-Jun\u00a0Angela Zhang and Jun Zhang. 2024. Green edge AI: A contemporary survey. Proc. IEEE (2024).","DOI":"10.1109\/JPROC.2024.3437365"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Stanislav Minsker. 2015. Geometric median and robust estimation in Banach spaces. Bernoulli 21 4 (2015) 2308\u20132335.","DOI":"10.3150\/14-BEJ645"},{"key":"e_1_3_3_3_28_2","series-title":"(ICML \u201917)","first-page":"2613","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Nguyen Lam\u00a0M.","year":"2017","unstructured":"Lam\u00a0M. Nguyen, Jie Liu, Katya Scheinberg, and Martin Tak\u00e1\u010d. 2017. SARAH: A novel method for machine learning problems using stochastic recursive gradient. In Proceedings of the 34th International Conference on Machine Learning(ICML \u201917). 2613\u20132621."},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746340"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Jie Peng Zhaoxian Wu Qing Ling and Tianyi Chen. 2022. Byzantine-robust variance-reduced federated learning over distributed non-iid data. Information Sciences 616 (2022) 367\u2013391.","DOI":"10.1016\/j.ins.2022.10.120"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"crossref","unstructured":"Dian Shi Liang Li Maoqiang Wu Minglei Shu Rong Yu and Miao Pan. 2022. To talk or to work: Dynamic batch sizes assisted time efficient federated learning over future mobile edge devices. IEEE Transactions on Wireless Communications 21 12 (2022) 11038\u201311050.","DOI":"10.1109\/TWC.2022.3189320"},{"key":"e_1_3_3_3_33_2","unstructured":"Jakub\u00a0Kacper Szelag Ji-Jian Chin and Sook-Chin Yip. 2025. Adaptive adversaries in Byzantine-robust federated learning: A survey. Cryptology ePrint Archive (2025)."},{"key":"e_1_3_3_3_34_2","unstructured":"Tsung-Hsuan Wang Po-Ning Chen and Yu-Chih Huang. 2025. Probabilistic Byzantine attack on federated learning. IEEE Transactions on Signal Processing (2025) 1\u201315."},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Zhaoxian Wu Tianyi Chen and Qing Ling. 2023. Byzantine-resilient decentralized stochastic optimization with robust aggregation rules. IEEE Transactions on Signal Processing 71 (2023) 3179\u20133195.","DOI":"10.1109\/TSP.2023.3300629"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Zhaoxian Wu Qing Ling Tianyi Chen and Georgios\u00a0B. Giannakis. 2020. Federated variance-reduced stochastic gradient descent with robustness to Byzantine attacks. IEEE Transactions on Signal Processing 68 (2020) 4583\u20134596.","DOI":"10.1109\/TSP.2020.3012952"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/670"},{"key":"e_1_3_3_3_38_2","unstructured":"Cong Xie Oluwasanmi Koyejo and Indranil Gupta. 2018. Generalized Byzantine-tolerant SGD. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1802.10116 (2018)."},{"key":"e_1_3_3_3_39_2","series-title":"(ICML \u201919)","first-page":"6893","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Xie Cong","year":"2019","unstructured":"Cong Xie, Sanmi Koyejo, and Indranil Gupta. 2019. Zeno: Distributed stochastic gradient descent with suspicion-based fault-tolerance. In Proceedings of the 36th International Conference on Machine Learning(ICML \u201919). PMLR, 6893\u20136901."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Gang Xu Lele Lei Yanhui Mao Zongpeng Li Xiu-Bo Chen and Kejia Zhang. 2025. CBRFL: A framework for committee-based Byzantine-resilient federated learning. Journal of Network and Computer Applications 238 (2025) 104165.","DOI":"10.1016\/j.jnca.2025.104165"},{"key":"e_1_3_3_3_41_2","series-title":"(ICLR \u201924)","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Yang Yi-Rui","year":"2024","unstructured":"Yi-Rui Yang, Chang-Wei Shi, and Wu-Jun Li. 2024. On the effect of batch size in Byzantine-robust distributed learning. In Proceedings of the International Conference on Learning Representations(ICLR \u201924)."},{"key":"e_1_3_3_3_42_2","series-title":"(ICLR \u201924)","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Yang Yi-Rui","year":"2024","unstructured":"Yi-Rui Yang, Chang-Wei Shi, and Wu-Jun Li. 2024. On the optimal batch size for Byzantine-robust distributed learning. In Proceedings of the International Conference on Learning Representations(ICLR \u201924)."},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"crossref","unstructured":"Haoxiang Ye and Qing Ling. 2025. Generalization error matters in decentralized learning under Byzantine attacks. IEEE Transactions on Signal Processing 73 (2025) 843\u2013857.","DOI":"10.1109\/TSP.2025.3526989"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"crossref","unstructured":"Heng Zhu and Qing Ling. 2023. Byzantine-robust distributed learning with compression. IEEE Transactions on Signal and Information Processing over Networks (2023).","DOI":"10.1109\/TSIPN.2023.3265892"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383346"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:10:23Z","timestamp":1765008623000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770940"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":44,"alternative-id":["10.1145\/3743093.3770940","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770940","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}