{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:20:22Z","timestamp":1791303622402,"version":"4.1.0"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100022210","name":"National Satellite of Excellence in Trustworthy Software Systems, National University of Singapore","doi-asserted-by":"publisher","award":["NRF2018NCR-NSOE003-0001"],"award-info":[{"award-number":["NRF2018NCR-NSOE003-0001"]}],"id":[{"id":"10.13039\/501100022210","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Nanyang Technological University, under SUG Grant","award":["020724-00001"],"award-info":[{"award-number":["020724-00001"]}]},{"name":"NRF Investigatorship","award":["NRF-NRFI06-2020-0001."],"award-info":[{"award-number":["NRF-NRFI06-2020-0001."]}]},{"name":"the Cyber Security Agency under its National Cybersecurity R&D Programme","award":["NCRP25-P04-TAICeN"],"award-info":[{"award-number":["NCRP25-P04-TAICeN"]}]},{"name":"National Research Foundation Singapore and DSO National Laboratories under the AI Singapore Programme","award":["AISG2-RP-2020-019"],"award-info":[{"award-number":["AISG2-RP-2020-019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2023,11,13]]},"abstract":"<jats:p>Federated Learning (FL) enables a large number of data owners (a.k.a. FL clients) to jointly train a machine learning model without disclosing private local data. The importance of local data samples to the FL model vary widely. This is exacerbated by the presence of noisy data, which exhibit large losses similar to important (hard) samples. Currently, there lacks an FL approach that can effectively distinguish hard samples (which are beneficial) from noisy samples (which are harmful). To bridge this gap, we propose the Federated Client and Sample Selection (FedCSS) approach. It is a bilevel optimization approach for FL client-and-sample selection to achieve hard sample-aware noise-robust learning in a privacy preserving manner. It performs meta-learning based online approximation to iteratively update global FL models, select the most positively influential samples and deal with training data noise. Theoretical analysis shows that it is guaranteed to converge in an efficient manner. Experimental comparison against six state-of-the-art baselines on five real-world datasets in the presence of data noise and heterogeneity shows that it achieves up to 26.4% higher test accuracy, while saving communication and computation costs by at least 41.5% and 1.2%, respectively.<\/jats:p>","DOI":"10.1145\/3617332","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T22:28:39Z","timestamp":1699914519000},"page":"1-24","source":"Crossref","is-referenced-by-count":11,"title":["FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning"],"prefix":"10.1145","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3592-4153","authenticated-orcid":false,"given":"Anran","family":"Li","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3785-7281","authenticated-orcid":false,"given":"Yue","family":"Cao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2855-4246","authenticated-orcid":false,"given":"Jiabao","family":"Guo","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2720-2628","authenticated-orcid":false,"given":"Hongyi","family":"Peng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0974-9299","authenticated-orcid":false,"given":"Qing","family":"Guo","sequence":"additional","affiliation":[{"name":"A*STAR, Singapore, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6893-8650","authenticated-orcid":false,"given":"Han","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"ICML","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, and Ramage. Communication-efficient learning of deep networks from decentralized data. In ICML, 2017."},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551798"},{"key":"e_1_2_2_3_1","volume-title":"Fedsdg-fs: Efficient and secure feature selection for vertical federated learning. arXiv preprint arXiv:2302.10417","author":"Li Anran","year":"2023","unstructured":"Anran Li, Hongyi Peng, Lan Zhang, Jiahui Huang, Qing Guo, Han Yu, and Yang Liu. Fedsdg-fs: Efficient and secure feature selection for vertical federated learning. arXiv preprint arXiv:2302.10417, 2023."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM56429.2023.10099110"},{"key":"e_1_2_2_5_1","volume-title":"DeepAI","author":"Hard Andrew","year":"2018","unstructured":"Andrew Hard, Kanishka Rao, Rajiv Mathews, and Ramaswamy. Federated learning for mobile keyboard prediction. DeepAI, 2018."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00120"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3046665"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC48107.2020.9148475"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01506-3"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488723"},{"key":"e_1_2_2_11_1","first-page":"2525","volume-title":"International conference on machine learning","author":"Katharopoulos Angelos","year":"2018","unstructured":"Angelos Katharopoulos and Fran\u00e7ois Fleuret. Not all samples are created equal: Deep learning with importance sampling. In International conference on machine learning, pages 2525--2534. PMLR, 2018."},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00028"},{"key":"e_1_2_2_13_1","volume-title":"On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189","author":"Li Xiang","year":"2019","unstructured":"Xiang Li, Kaixuan Huang, Wenhao Yang, and Shusen Wang. On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189, 2019."},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3137321"},{"key":"e_1_2_2_15_1","volume-title":"Fedmr: Federated learning via model recombination. arXiv preprint arXiv:2305.10730","author":"Hu Ming","year":"2023","unstructured":"Ming Hu, Zhihao Yue, Zhiwei Ling, Yihao Huang, Cheng Chen, Xian Wei, Yang Liu, and Mingsong Chen. Fedmr: Federated learning via model recombination. arXiv preprint arXiv:2305.10730, 2023."},{"key":"e_1_2_2_16_1","first-page":"872","volume-title":"International Conference on Machine Learning","author":"Byrd Jonathon","year":"2019","unstructured":"Jonathon Byrd and Zachary Lipton. What is the effect of importance weighting in deep learning? In International Conference on Machine Learning, pages 872--881. PMLR, 2019."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"e_1_2_2_18_1","volume-title":"Variance reduction in sgd by distributed importance sampling. arXiv preprint arXiv:1511.06481","author":"Alain Guillaume","year":"2015","unstructured":"Guillaume Alain, Alex Lamb, Chinnadhurai Sankar, Aaron Courville, and Yoshua Bengio. Variance reduction in sgd by distributed importance sampling. arXiv preprint arXiv:1511.06481, 2015."},{"key":"e_1_2_2_19_1","first-page":"19","volume-title":"15th {USENIX} Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Lai Fan","year":"2021","unstructured":"Fan Lai, Xiangfeng Zhu, Harsha V Madhyastha, and Mosharaf Chowdhury. Oort: Efficient federated learning via guided participant selection. In 15th {USENIX} Symposium on Operating Systems Design and Implementation (OSDI 21), pages 19--35, 2021."},{"key":"e_1_2_2_20_1","volume-title":"Luu Anh Tuan, and Han Yu. Towards interpretable federated learning. arXiv preprint arXiv:2302.13473","author":"Li Anran","year":"2023","unstructured":"Anran Li, Rui Liu, Ming Hu, Luu Anh Tuan, and Han Yu. Towards interpretable federated learning. arXiv preprint arXiv:2302.13473, 2023."},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_2_2_22_1","volume-title":"A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1):119--139","author":"Freund Yoav","year":"1997","unstructured":"Yoav Freund and Robert E Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1):119--139, 1997."},{"key":"e_1_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3125459"},{"key":"e_1_2_2_24_1","first-page":"2304","volume-title":"ICML","author":"Jiang Lu","year":"2018","unstructured":"Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, and Li Fei-Fei. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In ICML, pages 2304--2313. PMLR, 2018."},{"key":"e_1_2_2_25_1","volume-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems, 31","author":"Han Bo","year":"2018","unstructured":"Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, and Xu. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems, 31, 2018."},{"key":"e_1_2_2_26_1","volume-title":"Client selection in federated learning: Convergence analysis and power-of-choice selection strategies. arXiv preprint arXiv:2010.01243","author":"Cho Yae Jee","year":"2020","unstructured":"Yae Jee Cho, Jianyu Wang, and Gauri Joshi. Client selection in federated learning: Convergence analysis and power-of-choice selection strategies. arXiv preprint arXiv:2010.01243, 2020."},{"key":"e_1_2_2_27_1","volume-title":"Sample selection with deadline control for efficient federated learning on heterogeneous clients. arXiv preprint arXiv:2201.01601","author":"Shin Jaemin","year":"2022","unstructured":"Jaemin Shin, Yuanchun Li, Yunxin Liu, and Sung-Ju Lee. Sample selection with deadline control for efficient federated learning on heterogeneous clients. arXiv preprint arXiv:2201.01601, 2022."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21505"},{"key":"e_1_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00073"},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"e_1_2_2_31_1","volume-title":"Communication-efficient federated learning via optimal client sampling. arXiv preprint arXiv:2007.15197","author":"Ribero Monica","year":"2020","unstructured":"Monica Ribero and Haris Vikalo. Communication-efficient federated learning via optimal client sampling. arXiv preprint arXiv:2007.15197, 2020."},{"key":"e_1_2_2_32_1","volume-title":"Federated learning: Collaborative machine learning without centralized training data. https:\/\/ai.googleblog.com\/2017\/04\/federated-learning-collaborative.html","author":"Google","year":"2017","unstructured":"Google AI. Federated learning: Collaborative machine learning without centralized training data. https:\/\/ai.googleblog.com\/2017\/04\/federated-learning-collaborative.html, 2017."},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00039"},{"key":"e_1_2_2_34_1","volume-title":"Is your data relevant?: Dynamic selection of relevant data for federated learning","author":"Nagalapatti Lokesh","year":"2022","unstructured":"Lokesh Nagalapatti and Ruhi Sharma Mittal. Is your data relevant?: Dynamic selection of relevant data for federated learning. 2022."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_2_2_36_1","first-page":"1311","volume-title":"international conference on machine learning","author":"Graves Alex","year":"2017","unstructured":"Alex Graves, Marc G Bellemare, Jacob Menick, Remi Munos, and Koray Kavukcuoglu. Automated curriculum learning for neural networks. In international conference on machine learning, pages 1311--1320. PMLR, 2017."},{"key":"e_1_2_2_37_1","first-page":"1","volume-title":"Transferable latent of cnn-based selective fixed-filter active noise control","author":"Shi Dongyuan","year":"2023","unstructured":"Dongyuan Shi, Woon-Seng Gan, Bhan Lam, Zhengding Luo, and Xiaoyi Shen. Transferable latent of cnn-based selective fixed-filter active noise control. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, pages 1--12, 2023."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.08.043"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"e_1_2_2_40_1","first-page":"30","article-title":"Training more accurate neural networks by emphasizing high variance samples","author":"Chang Haw-Shiuan","year":"2017","unstructured":"Haw-Shiuan Chang, Erik Learned-Miller, and Andrew McCallum. Active bias: Training more accurate neural networks by emphasizing high variance samples. Advances in Neural Information Processing Systems, 30, 2017.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_2_41_1","volume-title":"Using trusted data to train deep networks on labels corrupted by severe noise. Advances in neural information processing systems, 31","author":"Hendrycks Dan","year":"2018","unstructured":"Dan Hendrycks, Mantas Mazeika, Duncan Wilson, and Kevin Gimpel. Using trusted data to train deep networks on labels corrupted by severe noise. Advances in neural information processing systems, 31, 2018."},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_2_43_1","volume-title":"International Conference on Learning Representations","author":"Balakrishnan Ravikumar","year":"2021","unstructured":"Ravikumar Balakrishnan, Tian Li, Zhou, and Jeff Bilmes. Diverse client selection for federated learning via submodular maximization. In International Conference on Learning Representations, 2021."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412599"},{"key":"e_1_2_2_45_1","volume-title":"Fednest: Federated bilevel, minimax, and compositional optimization. arXiv preprint arXiv:2205.02215","author":"Tarzanagh Davoud Ataee","year":"2022","unstructured":"Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, and Samet Oymak. Fednest: Federated bilevel, minimax, and compositional optimization. arXiv preprint arXiv:2205.02215, 2022."},{"key":"e_1_2_2_46_1","first-page":"1540","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Lorraine Jonathan","year":"2020","unstructured":"Jonathan Lorraine, Paul Vicol, and David Duvenaud. Optimizing millions of hyperparameters by implicit differentiation. In International Conference on Artificial Intelligence and Statistics, pages 1540--1552. PMLR, 2020."},{"key":"e_1_2_2_47_1","first-page":"1885","volume-title":"International conference on machine learning","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. Understanding black-box predictions via influence functions. In International conference on machine learning, pages 1885--1894. PMLR, 2017."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1980.10486199"},{"key":"e_1_2_2_49_1","volume-title":"On the accuracy of influence functions for measuring group effects. Advances in neural information processing systems, 32","author":"Koh Pang Wei W","year":"2019","unstructured":"Pang Wei W Koh, Kai-Siang Ang, Hubert Teo, and Percy S Liang. On the accuracy of influence functions for measuring group effects. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_2_2_50_1","first-page":"1126","volume-title":"International conference on machine learning","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, pages 1126--1135. PMLR, 2017."},{"key":"e_1_2_2_51_1","volume-title":"Differentially private federated learning: A client level perspective. arXiv preprint arXiv:1712.07557","author":"Geyer Robin C","year":"2017","unstructured":"Robin C Geyer, Tassilo Klein, and Moin Nabi. Differentially private federated learning: A client level perspective. arXiv preprint arXiv:1712.07557, 2017."},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_2_2_53_1","volume-title":"The algorithmic foundations of differential privacy. Foundations and Trends\u00ae in Theoretical Computer Science, 9(3--4):211--407","author":"Dwork Cynthia","year":"2014","unstructured":"Cynthia Dwork, Aaron Roth, et al. The algorithmic foundations of differential privacy. Foundations and Trends\u00ae in Theoretical Computer Science, 9(3--4):211--407, 2014."},{"key":"e_1_2_2_54_1","volume-title":"Public online","year":"2022","unstructured":"Pytorch. Pytorch. Public online, 2022."},{"key":"e_1_2_2_55_1","unstructured":"Yann LeCun. The mnist database of handwritten digits. http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"e_1_2_2_56_1","volume-title":"Peter Wu, Tian Li, Jakub Konecny, H Brendan McMahan, Virginia Smith, and Ameet Talwalkar. Leaf: A benchmark for federated settings. arXiv preprint arXiv:1812.01097","author":"Caldas Sebastian","year":"2018","unstructured":"Sebastian Caldas, Sai Meher Karthik Duddu, Peter Wu, Tian Li, Jakub Konecny, H Brendan McMahan, Virginia Smith, and Ameet Talwalkar. Leaf: A benchmark for federated settings. arXiv preprint arXiv:1812.01097, 2018."},{"key":"e_1_2_2_57_1","unstructured":"Sai Meher Karthik Duddu Sebastian Caldas. Leaf: A benchmark for federated settings. https:\/\/leaf.cmu.edu\/."},{"key":"e_1_2_2_58_1","volume-title":"Learning multiple layers of features from tiny images. semanticscholar","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny images. semanticscholar, 2009."},{"key":"e_1_2_2_59_1","unstructured":"Alex Krizhevsky et al. Cifar-100 dataset. cs.toronto.edu\/~kriz\/cifar.html."},{"key":"e_1_2_2_60_1","unstructured":"Antonio Gulli. Ag's corpus of news articles. http:\/\/groups.di.unipi.it\/~gulli\/AG_corpus_of_news_articles.html."},{"key":"e_1_2_2_61_1","first-page":"4334","volume-title":"International conference on machine learning","author":"Ren Mengye","year":"2018","unstructured":"Mengye Ren, Wenyuan Zeng, Bin Yang, and Raquel Urtasun. Learning to reweight examples for robust deep learning. In International conference on machine learning, pages 4334--4343. PMLR, 2018."},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_2_63_1","unstructured":"Ben Trevett. Sentiment analysis. https:\/\/github.com\/bentrevett\/pytorch-sentiment-analysis\/blob\/master\/6%20-%20Transformers%20for%20Sentiment%20Analysis.ipynb."},{"key":"e_1_2_2_64_1","volume-title":"Focus: Dealing with label quality disparity in federated learning. arXiv preprint arXiv:2001.11359","author":"Chen Yiqiang","year":"2020","unstructured":"Yiqiang Chen, Xiaodong Yang, Xin Qin, Han Yu, Biao Chen, and Zhiqi Shen. Focus: Dealing with label quality disparity in federated learning. arXiv preprint arXiv:2001.11359, 2020."},{"key":"e_1_2_2_65_1","volume-title":"Salman Avestimehr, and Tao Zhang. Actperfl: Active personalized federated learning.","author":"Chen Huili","year":"2022","unstructured":"Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, and Tao Zhang. Actperfl: Active personalized federated learning. 2022."},{"key":"e_1_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517836"}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617332","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617332","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:45:53Z","timestamp":1750178753000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617332"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"references-count":66,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,11,13]]}},"alternative-id":["10.1145\/3617332"],"URL":"https:\/\/doi.org\/10.1145\/3617332","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,13]]}}}