{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T22:32:10Z","timestamp":1778193130158,"version":"3.51.4"},"reference-count":28,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T00:00:00Z","timestamp":1663804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["42050101 and 61721003"],"award-info":[{"award-number":["42050101 and 61721003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2022,12,31]]},"abstract":"<jats:p>Federated learning (FL) is a privacy-preserving paradigm for multi-institutional collaborations, where the aggregation is an essential procedure after training on the local datasets. Conventional aggregation algorithms often apply a weighted averaging of the updates generated from distributed machines to update the global model. However, while the data distributions are non-IID, the large discrepancy between the local updates might lead to a poor averaged result and a lower convergence speed, i.e., more iterations required to achieve a certain performance. To solve this problem, this article proposes a novel method named AggEnhance for enhancing the aggregation, where we synthesize a group of reliable samples from the local models and tune the aggregated result on them. These samples, named class interior points (CIPs) in this work, bound the relevant decision boundaries that ensure the performance of aggregated result. To the best of our knowledge, this is the first work to explicitly design an enhancing method for the aggregation in prevailing FL pipelines. A series of experiments on real data demonstrate that our method has noticeable improvements of the convergence in non-IID scenarios. In particular, our approach reduces the iterations by 31.87% on average for the CIFAR10 dataset and 43.90% for the PASCAL VOC dataset. Since our method does not modify other procedures of FL pipelines, it is easy to apply to most existing FL frameworks. Furthermore, it does not require additional data transmitted from the local clients to the global server, thus holding the same security level as the original FL algorithms.<\/jats:p>","DOI":"10.1145\/3544495","type":"journal-article","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T10:07:17Z","timestamp":1655374037000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["AggEnhance: Aggregation Enhancement by Class Interior Points in Federated Learning with Non-IID Data"],"prefix":"10.1145","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8002-9302","authenticated-orcid":false,"given":"Jinxiang","family":"Ou","sequence":"first","affiliation":[{"name":"Tsinghua University, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1961-0274","authenticated-orcid":false,"given":"Yunheng","family":"Shen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7553-3184","authenticated-orcid":false,"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9781-3360","authenticated-orcid":false,"given":"Qiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9684-5643","authenticated-orcid":false,"given":"Xuegong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1568-6861","authenticated-orcid":false,"given":"Hairong","family":"Lv","sequence":"additional","affiliation":[{"name":"Tsinghua University, Haidian, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,9,22]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_3_2","article-title":"Robust federated learning in a heterogeneous environment","author":"Ghosh Avishek","year":"2019","unstructured":"Avishek Ghosh, Justin Hong, Dong Yin, and Kannan Ramchandran. 2019. Robust federated learning in a heterogeneous environment. arXiv preprint arXiv:1906.06629 (2019).","journal-title":"arXiv preprint arXiv:1906.06629"},{"key":"e_1_3_2_4_2","article-title":"Active federated learning","author":"Goetz Jack","year":"2019","unstructured":"Jack Goetz, Kshitiz Malik, Duc Bui, Seungwhan Moon, Honglei Liu, and Anuj Kumar. 2019. Active federated learning. arXiv preprint arXiv:1909.12641 (2019).","journal-title":"arXiv preprint arXiv:1909.12641"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"e_1_3_2_6_2","article-title":"One-shot federated learning","author":"Guha Neel","year":"2019","unstructured":"Neel Guha, Ameet Talwalkar, and Virginia Smith. 2019. One-shot federated learning. arXiv preprint arXiv:1902.11175 (2019).","journal-title":"arXiv preprint arXiv:1902.11175"},{"key":"e_1_3_2_7_2","article-title":"Federated learning for mobile keyboard prediction","author":"Hard Andrew","year":"2018","unstructured":"Andrew Hard, Kanishka Rao, Rajiv Mathews, Swaroop Ramaswamy, Fran\u00e7oise Beaufays, Sean Augenstein, Hubert Eichner, Chlo\u00e9 Kiddon, and Daniel Ramage. 2018. Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604 (2018).","journal-title":"arXiv preprint arXiv:1811.03604"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_9_2","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu Tzu-Ming Harry","year":"2019","unstructured":"Tzu-Ming Harry Hsu, Hang Qi, and Matthew Brown. 2019. Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335 (2019).","journal-title":"arXiv preprint arXiv:1909.06335"},{"key":"e_1_3_2_10_2","first-page":"448","volume-title":"International Conference on Machine Learning","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. PMLR, 448\u2013456."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0186-1"},{"key":"e_1_3_2_12_2","first-page":"5381","volume-title":"International Conference on Machine Learning","author":"Koloskova Anastasia","year":"2020","unstructured":"Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, and Sebastian Stich. 2020. A unified theory of decentralized SGD with changing topology and local updates. In International Conference on Machine Learning. PMLR, 5381\u20135393."},{"key":"e_1_3_2_13_2","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. Ph. D. Dissertation. University of Toronto."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683546"},{"key":"e_1_3_2_16_2","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li Tian","year":"2020","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. Proc. Mach. Learn. Syst. 2 (2020), 429\u2013450.","journal-title":"Proc. Mach. Learn. Syst."},{"key":"e_1_3_2_17_2","first-page":"133","volume-title":"International Workshop on Machine Learning in Medical Imaging","author":"Li Wenqi","year":"2019","unstructured":"Wenqi Li, Fausto Milletar\u00ec, Daguang Xu, Nicola Rieke, Jonny Hancox, Wentao Zhu, Maximilian Baust, Yan Cheng, S\u00e9bastien Ourselin, M. Jorge Cardoso, et\u00a0al. 2019. Privacy-preserving federated brain tumour segmentation. In International Workshop on Machine Learning in Medical Imaging. Springer, 133\u2013141."},{"key":"e_1_3_2_18_2","volume-title":"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 International Conference on Learning Representations."},{"key":"e_1_3_2_19_2","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Liang Paul Pu","year":"2020","unstructured":"Paul Pu Liang, Terrance Liu, Liu Ziyin, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2020. Think locally, act globally: Federated learning with local and global representations. arXiv preprint arXiv:2001.01523 (2020).","journal-title":"arXiv preprint arXiv:2001.01523"},{"key":"e_1_3_2_20_2","first-page":"1273","volume-title":"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 Artificial Intelligence and Statistics. PMLR, 1273\u20131282."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00323-1"},{"key":"e_1_3_2_22_2","first-page":"92","volume-title":"International MICCAI Brainlesion Workshop","author":"Sheller Micah J.","year":"2018","unstructured":"Micah J. Sheller, G. Anthony Reina, Brandon Edwards, Jason Martin, and Spyridon Bakas. 2018. Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation. In International MICCAI Brainlesion Workshop. Springer, 92\u2013104."},{"key":"e_1_3_2_23_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).","journal-title":"arXiv preprint arXiv:1409.1556"},{"key":"e_1_3_2_24_2","volume-title":"International Conference on Learning Representations","author":"Wang Hongyi","year":"2020","unstructured":"Hongyi Wang, Mikhail Yurochkin, Yuekai Sun, Dimitris Papailiopoulos, and Yasaman Khazaeni. 2020. Federated learning with matched averaging. In International Conference on Learning Representations."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"e_1_3_2_26_2","first-page":"5650","volume-title":"International Conference on Machine Learning","author":"Yin Dong","year":"2018","unstructured":"Dong Yin, Yudong Chen, Ramchandran Kannan, and Peter Bartlett. 2018. Byzantine-robust distributed learning: Towards optimal statistical rates. In International Conference on Machine Learning. PMLR, 5650\u20135659."},{"key":"e_1_3_2_27_2","article-title":"Federated learning with non-IID data","author":"Zhao Yue","year":"2018","unstructured":"Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra. 2018. Federated learning with non-IID data. arXiv preprint arXiv:1806.00582 (2018).","journal-title":"arXiv preprint arXiv:1806.00582"},{"key":"e_1_3_2_28_2","article-title":"Distilled one-shot federated learning","author":"Zhou Yanlin","year":"2020","unstructured":"Yanlin Zhou, George Pu, Xiyao Ma, Xiaolin Li, and Dapeng Wu. 2020. Distilled one-shot federated learning. arXiv preprint arXiv:2009.07999 (2020).","journal-title":"arXiv preprint arXiv:2009.07999"},{"key":"e_1_3_2_29_2","volume-title":"Advances in Neural Information Processing Systems","author":"Zhu Ligeng","year":"2019","unstructured":"Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep leakage from gradients. In Advances in Neural Information Processing Systems, Vol. 32."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544495","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3544495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:54Z","timestamp":1750186974000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,22]]},"references-count":28,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12,31]]}},"alternative-id":["10.1145\/3544495"],"URL":"https:\/\/doi.org\/10.1145\/3544495","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,22]]},"assertion":[{"value":"2021-07-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-08","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}