{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:16:32Z","timestamp":1773951392705,"version":"3.50.1"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP), grant funded by the Korea Government","award":["RS-2022-00155915"],"award-info":[{"award-number":["RS-2022-00155915"]}]},{"name":"Artificial Intelligence Convergence Innovation Human Resources Development"},{"name":"National Research Foundation of Korea (NRF), grant funded by the Korea Government","award":["No. RS-2024-00452914"],"award-info":[{"award-number":["No. RS-2024-00452914"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>\n                    While unbiased gradient estimators ensure unbiased solutions in empirical risk minimization problems, they can significantly hinder optimization efficiency and generalization performance in strongly non-IID Federated Learning environments. Although recent studies have demonstrated promising applications of biased estimators, they typically focus only on convergence rates while overlooking generalization performance. We propose a novel multi-metric bias concept, quantified using both local loss and local gradient norm, along with a client activation method based on this bias concept. The proposed method prioritizes training on local datasets that better represent the global dataset, leading to faster convergence and improved generalization. Our extensive empirical study demonstrates that carefully injecting bias into client activation accelerates federated optimization, achieving a substantially improved validation accuracy within a given epoch budget. In representative machine learning benchmarks, our method achieves up to\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(12.7\\%\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    higher accuracy than uniform random sampling and\n                    <jats:inline-formula content-type=\"math\/tex\">\n                      <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\(2.5\\%\\)<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    higher accuracy than state-of-the-art biased client activation methods.\n                  <\/jats:p>","DOI":"10.1145\/3793668","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T14:11:49Z","timestamp":1770127909000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Metric Client Activation Method for Fast and Accurate Federated Learning"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1668-3762","authenticated-orcid":false,"given":"Jihyun","family":"Lim","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Inha University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3676-0717","authenticated-orcid":false,"given":"Tuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"ECE Department, University of Southern California, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6334-3068","authenticated-orcid":false,"given":"Sunwoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Inha University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the Workshop on \u201cBeyond First Order Methods in ML Systems\u201d at International Conference on Machine Learning","author":"Ajalloeian Ahmad","year":"2020","unstructured":"Ahmad Ajalloeian and Sebastian U. Stich. 2020. On the convergence of SGD with biased gradients. In Proceedings of the Workshop on \u201cBeyond First Order Methods in ML Systems\u201d at International Conference on Machine Learning."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2600425"},{"key":"e_1_3_2_4_2","unstructured":"Sebastian Caldas Sai Meher Karthik Duddu Peter Wu Tian Li Jakub Kone\u010dn\u1ef3 H. Brendan McMahan Virginia Smith and Ameet Talwalkar. 2018. Leaf: A benchmark for federated settings. arXiv:1812.01097. Retrieved from https:\/\/arxiv.org\/abs\/1812.01097"},{"key":"e_1_3_2_5_2","volume-title":"Proceedings of 11th International Conference on Learning Representations","author":"Chiang Ping-Yeh","year":"2022","unstructured":"Ping-Yeh Chiang, Renkun Ni, David Yu Miller, Arpit Bansal, Jonas Geiping, Micah Goldblum, and Tom Goldstein. 2022. Loss landscapes are all you need: Neural network generalization can be explained without the implicit bias of gradient descent. In Proceedings of 11th International Conference on Learning Representations."},{"key":"e_1_3_2_6_2","first-page":"10351","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Cho Yae Jee","year":"2022","unstructured":"Yae Jee Cho, Jianyu Wang, and Gauri Joshi. 2022. Towards understanding biased client selection in federated learning. In Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 10351\u201310375."},{"issue":"1","key":"e_1_3_2_7_2","first-page":"1057","article-title":"On biased stochastic gradient estimation","volume":"23","author":"Driggs Derek","year":"2022","unstructured":"Derek Driggs, Jingwei Liang, and Carola-Bibiane Sch\u00f6nlieb. 2022. On biased stochastic gradient estimation. Journal of Machine Learning Research 23, 1 (2022), 1057\u20131099.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_8_2","volume-title":"Proceedings of the International Conference on Learning Representation","author":"Foret Pierre","year":"2021","unstructured":"Pierre Foret, Ariel Kleiner, Hossein Mobahi, and Behnam Neyshabur. 2021. Sharpness-aware minimization for efficiently improving generalization. In Proceedings of the International Conference on Learning Representation."},{"key":"e_1_3_2_9_2","first-page":"3407","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Fraboni Yann","year":"2021","unstructured":"Yann Fraboni, Richard Vidal, Laetitia Kameni, and Marco Lorenzi. 2021. Clustered sampling: Low-variance and improved representativity for clients selection in federated learning. In Proceedings of the International Conference on Machine Learning. PMLR, 3407\u20133416."},{"key":"e_1_3_2_10_2","unstructured":"Jack Goetz Kshitiz Malik Duc Bui Seungwhan Moon Honglei Liu and Anuj Kumar. 2019. Active federated learning. arXiv:1909.12641. Retrieved from https:\/\/arxiv.org\/abs\/1909.12641"},{"key":"e_1_3_2_11_2","unstructured":"Endong Gu Yongxin Chen Hao Wen Xingju Cai and Deren Han. 2024. Novel clustered federated learning based on local loss. arXiv:2407.09360. Retrieved from https:\/\/arxiv.org\/abs\/2407.09360"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of 5th International Conference on Learning Representations","author":"Keskar Nitish Shirish","year":"2017","unstructured":"Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, and Ping Tak Peter Tang. 2017. On large-batch training for deep learning: Generalization gap and sharp minima. In Proceedings of 5th International Conference on Learning Representations."},{"key":"e_1_3_2_15_2","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report TR-2009 University of Toronto Toronto."},{"key":"e_1_3_2_16_2","first-page":"19","volume-title":"Proceedings of 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201921)","author":"Lai Fan","year":"2021","unstructured":"Fan Lai, Xiangfeng Zhu, Harsha V. Madhyastha, and Mosharaf Chowdhury. 2021. Oort: Efficient federated learning via guided participant selection. In Proceedings of 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201921), 19\u201335."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.11.007"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006550"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126647"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3392212"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517017"},{"key":"e_1_3_2_22_2","volume-title":"Proceedings of 8th International Conference on Learning Representations","author":"Li Xiang","year":"2020","unstructured":"Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. 2020. On the convergence of FedAvg on non-IID data. In Proceedings of 8th International Conference on Learning Representations."},{"key":"e_1_3_2_23_2","unstructured":"Xianfeng Liang Shuheng Shen Jingchang Liu Zhen Pan Enhong Chen and Yifei Cheng. 2019. Variance reduced local SGD with lower communication complexity. arXiv:1912.12844. Retrieved from https:\/\/arxiv.org\/abs\/1912.12844"},{"key":"e_1_3_2_24_2","first-page":"1273","volume-title":"Proceedings of the Artificial Intelligence and Statistics","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the Artificial Intelligence and Statistics. PMLR, 1273\u20131282."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1014897230089"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/462"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15180"},{"key":"e_1_3_2_28_2","volume-title":"Proceedings of 9th International Conference on Learning Representations","author":"Reddi Sashank","year":"2021","unstructured":"Sashank Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Kone\u010dn\u1ef3, Sanjiv Kumar, and H. Brendan McMahan. 2021. Adaptive federated optimization. In Proceedings of 9th International Conference on Learning Representations."},{"key":"e_1_3_2_29_2","first-page":"2021","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Reisizadeh Amirhossein","year":"2020","unstructured":"Amirhossein Reisizadeh, Aryan Mokhtari, Hamed Hassani, Ali Jadbabaie, and Ramtin Pedarsani. 2020. FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization. In Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 2021\u20132031."},{"key":"e_1_3_2_30_2","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin et al. 2015. TensorFlow: Large-scale machine learning on heterogeneous systems. White Paper. Retrieved from https:\/\/www.tensorflow.org\/datasets"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"issue":"1","key":"e_1_3_2_32_2","first-page":"9709","article-title":"Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms","volume":"22","author":"Wang Jianyu","year":"2021","unstructured":"Jianyu Wang and Gauri Joshi. 2021. Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms. Journal of Machine Learning Research 22, 1 (2021), 9709\u20139758.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_33_2","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"33","author":"Wang Jianyu","year":"2020","unstructured":"Jianyu Wang, Qinghua Liu, Hao Liang, Gauri Joshi, and H. Vincent Poor. 2020. Tackling the objective inconsistency problem in heterogeneous federated optimization. Advances in Neural Information Processing Systems 33 (2020), 7611\u20137623.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_34_2","unstructured":"Pete Warden. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv:1804.03209. Retrieved from https:\/\/arxiv.org\/abs\/1804.03209"},{"key":"e_1_3_2_35_2","unstructured":"Lei Wu Zhanxing Zhu and E. Weinan 2017. Towards understanding generalization of deep learning: Perspective of loss landscapes. arXiv:1706.10239. Retrieved from https:\/\/arxiv.org\/abs\/1706.10239"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3516692"},{"key":"e_1_3_2_37_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Yang Haibo","year":"2021","unstructured":"Haibo Yang, Minghong Fang, and Jia Liu. 2021. Achieving linear speedup with partial worker participation in non-IID federated learning. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_38_2","first-page":"5332","article-title":"Federated accelerated stochastic gradient descent","volume":"33","author":"Yuan Honglin","year":"2020","unstructured":"Honglin Yuan and Tengyu Ma. 2020. Federated accelerated stochastic gradient descent. Advances in Neural Information Processing Systems 33 (2020), 5332\u20135344.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_39_2","first-page":"10752","article-title":"On convergence of FedProx: Local dissimilarity invariant bounds, non-smoothness and beyond","volume":"35","author":"Yuan Xiaotong","year":"2022","unstructured":"Xiaotong Yuan and Ping Li. 2022. On convergence of FedProx: Local dissimilarity invariant bounds, non-smoothness and beyond. Advances in Neural Information Processing Systems 35 (2022), 10752\u201310765.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01932"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01939"},{"key":"e_1_3_2_43_2","first-page":"26982","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zhao Yang","year":"2022","unstructured":"Yang Zhao, Hao Zhang, and Xiuyuan Hu. 2022. Penalizing gradient norm for efficiently improving generalization in deep learning. In Proceedings of the International Conference on Machine Learning, 26982\u201326992."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:30:42Z","timestamp":1773937842000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3793668"],"URL":"https:\/\/doi.org\/10.1145\/3793668","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"2025-02-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}