{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:32:03Z","timestamp":1774539123170,"version":"3.50.1"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T00:00:00Z","timestamp":1686787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61932013, 62061146002, 62225204"],"award-info":[{"award-number":["61932013, 62061146002, 62225204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2021308"],"award-info":[{"award-number":["CX2021308"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2023,8,31]]},"abstract":"<jats:p>Federated learning, as a distributed machine learning framework, enables clients to conduct model training without transmitting their data to the server, which is used to solve the dilemma of data silos and data privacy. It can work well on clients having similar data characteristics and distribution. However, it has some limitations where the dataset of clients may be different in distribution, quantity, and concept in many application scenarios. Personalized federated learning is a new federated learning paradigm that aims to guarantee client personalized models\u2019 effectiveness when collaborating with the cloud server. Intuitively, providing further facilitated collaborations for the clients with similar data characteristics and distribution can benefit personalized model building. However, due to the invisibility of client data, it is challenging to extract client characteristics and define collaborative relationships among them from a fine-grained view. Moreover, a reasonable collaborative training approach needs to be designed for a distributed server\u2013client framework. In this article, we design a Hierarchical Attention-enhanced Meta-learning Network\u00a0(HAM) to address this issue. The main advantage of HAM is that it utilizes the meta-learning approach of taking model parameters as features and learns to learn an extra model for each client to analyze similarities according to their local dataset automatically. According to its two-layers framework, HAM can reasonably achieve a tradeoff between clients\u2019 personality and commonality and provides a hybrid model with useful information from all clients. Considering there are two networks (HAM and base network) that need to learn for each client during the federated training process, we then provide an alternative learning approach to train them in an end-to-end fashion. To further clarify the approach, we describe the personalized federated learning settings framework as FedHAM where the HAM network is distributed deployed in each client. Extensive experiments based on two datasets prove that our method outperforms state-of-the-art baselines under different evaluation metrics.<\/jats:p>","DOI":"10.1145\/3591362","type":"journal-article","created":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T12:21:23Z","timestamp":1682079683000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Configure Your Federation: Hierarchical Attention-enhanced Meta-Learning Network for Personalized Federated Learning"],"prefix":"10.1145","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6380-1292","authenticated-orcid":false,"given":"Yujia","family":"Gao","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8658-7102","authenticated-orcid":false,"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5040-2468","authenticated-orcid":false,"given":"Liang","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8605-3848","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7199-5047","authenticated-orcid":false,"given":"Huadong","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,15]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2594132"},{"key":"e_1_3_2_4_2","unstructured":"Manoj Ghuhan Arivazhagan Vinay Aggarwal Aaditya Kumar Singh and Sunav Choudhary. 2019. Federated learning with personalization layers. arXiv: 1912.00818. Retrieved from https:\/\/arxiv.org\/abs\/1912.00818."},{"key":"e_1_3_2_5_2","unstructured":"Irwan Bello Barret Zoph Vijay Vasudevan and Quoc V. Le. 2017. Neural optimizer search with reinforcement learning. (unpublished)."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42488-020-00027-x"},{"key":"e_1_3_2_7_2","unstructured":"Keith Bonawitz Hubert Eichner Wolfgang Grieskamp Dzmitry Huba Alex Ingerman Vladimir Ivanov Chloe Kiddon Jakub Kone\u010dn\u1ef3 Stefano Mazzocchi H. Brendan McMahan et\u00a0al. 2019. Towards federated learning at scale: System design. (unpublished)."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1057"},{"key":"e_1_3_2_9_2","article-title":"On bridging generic and personalized federated learning","author":"Chen Hong-You","year":"2021","unstructured":"Hong-You Chen and Wei-Lun Chao. 2021. On bridging generic and personalized federated learning. arXiv:2107.00778. Retrieved from https:\/\/arxiv.org\/abs\/2107.00778.","journal-title":"arXiv:2107.00778"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2988604"},{"key":"e_1_3_2_11_2","unstructured":"Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. (unpublished)."},{"key":"e_1_3_2_12_2","first-page":"2089","volume-title":"International Conference on Machine Learning","author":"Collins Liam","year":"2021","unstructured":"Liam Collins, Hamed Hassani, Aryan Mokhtari, and Sanjay Shakkottai. 2021. Exploiting shared representations for personalized federated learning. In International Conference on Machine Learning. PMLR, 2089\u20132099."},{"key":"e_1_3_2_13_2","article-title":"Personalized federated learning: A meta-learning approach","author":"Fallah Alireza","year":"2020","unstructured":"Alireza Fallah, Aryan Mokhtari, and Asuman Ozdaglar. 2020. Personalized federated learning: A meta-learning approach. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201920).","journal-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201920)"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3381006"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"e_1_3_2_16_2","unstructured":"Filip Hanzely and Peter Richt\u00e1rik. 2020. Federated learning of a mixture of global and local models. (unpublished)."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"e_1_3_2_18_2","first-page":"5400","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201918)","author":"Houthooft Rein","year":"2018","unstructured":"Rein Houthooft, Yuhua Chen, Phillip Isola, Bradly Stadie, Filip Wolski, Jonathan Ho, and Pieter Abbeel. 2018. Evolved policy gradients. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201918). 5400\u20135409."},{"issue":"10","key":"e_1_3_2_19_2","first-page":"9530","article-title":"Personalized federated learning with differential privacy","volume":"7","author":"Hu Rui","year":"2020","unstructured":"Rui Hu, Yuanxiong Guo, Hongning Li, Qingqi Pei, and Yanmin Gong. 2020. Personalized federated learning with differential privacy. IEEE IoT J. 7, 10 (2020), 9530\u20139539.","journal-title":"IEEE IoT J."},{"key":"e_1_3_2_20_2","article-title":"Personalized cross-silo federated learning on Non-IID data","author":"Huang Yutao","year":"2020","unstructured":"Yutao Huang, Lingyang Chu, Zirui Zhou, Lanjun Wang, Jiangchuan Liu, Jian Pei, and Yong Zhang. 2020. Personalized cross-silo federated learning on Non-IID data. In Proceedings of the AAAI Annual Conference on Artificial Intelligence (AAAI\u201920) (2020).","journal-title":"Proceedings of the AAAI Annual Conference on Artificial Intelligence (AAAI\u201920)"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"e_1_3_2_22_2","unstructured":"Yihan Jiang Jakub Kone\u010dn\u1ef3 Keith Rush and Sreeram Kannan. 2019. Improving federated learning personalization via model agnostic meta learning. (unpublished)."},{"key":"e_1_3_2_23_2","unstructured":"Peter Kairouz H. Brendan McMahan Brendan Avent Aur\u00e9lien Bellet Mehdi Bennis Arjun Nitin Bhagoji Keith Bonawitz Zachary Charles Graham Cormode Rachel Cummings et\u00a0al. 2019. Advances and open problems in federated learning. (unpublished)."},{"key":"e_1_3_2_24_2","first-page":"5917","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201919)","author":"Khodak Mikhail","year":"2019","unstructured":"Mikhail Khodak, Maria-Florina F. Balcan, and Ameet S. Talwalkar. 2019. Adaptive gradient-based meta-learning methods. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201919). 5917\u20135928."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/3477.764879"},{"key":"e_1_3_2_26_2","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems. 1097\u20131105."},{"key":"e_1_3_2_27_2","unstructured":"Yann LeCun. 1998. The MNIST Database of Handwritten Digits. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/."},{"key":"e_1_3_2_28_2","article-title":"DALC: Distributed automatic LSTM customization for fine-grained traffic speed prediction","author":"Lee Ming-Chang","year":"2020","unstructured":"Ming-Chang Lee and Jia-Chun Lin. 2020. DALC: Distributed automatic LSTM customization for fine-grained traffic speed prediction. arXiv:2001.09821. Retrieved from https:\/\/arxiv.org\/abs\/2001.09821.","journal-title":"arXiv:2001.09821"},{"key":"e_1_3_2_29_2","unstructured":"Tian Li Anit Kumar Sahu Manzil Zaheer Maziar Sanjabi Ameet Talwalkar and Virginia Smith. 2018. Federated optimization in heterogeneous networks. (unpublished)."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6816"},{"key":"e_1_3_2_31_2","article-title":"Ensemble distillation for robust model fusion in federated learning","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Lingjing Kong, Sebastian U. Stich, and Martin Jaggi. 2020. Ensemble distillation for robust model fusion in federated learning. arXiv:2006.07242. Retrieved from https:\/\/arxiv.org\/abs\/2006.07242.","journal-title":"arXiv:2006.07242"},{"key":"e_1_3_2_32_2","article-title":"Heterogeneous model fusion federated learning mechanism based on model mapping","author":"Lu Xiaofeng","year":"2021","unstructured":"Xiaofeng Lu, Yuying Liao, Chao Liu, Pietro Lio, and Pan Hui. 2021. Heterogeneous model fusion federated learning mechanism based on model mapping. IEEE IoT J. (2021).","journal-title":"IEEE IoT J."},{"key":"e_1_3_2_33_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. 1273\u20131282."},{"key":"e_1_3_2_34_2","article-title":"GB 3095-2012 Ambient Air Quality Standards","author":"MEP AQSIQ","year":"2012","unstructured":"AQSIQ MEP. 2012. GB 3095-2012 Ambient Air Quality Standards. China Environmental Science Press, Beijing (2012).","journal-title":"China Environmental Science Press, Beijing"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.10.007"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761315"},{"key":"e_1_3_2_37_2","article-title":"Fedbabu: Towards enhanced representation for federated image classification","author":"Oh Jaehoon","year":"2021","unstructured":"Jaehoon Oh, Sangmook Kim, and Se-Young Yun. 2021. Fedbabu: Towards enhanced representation for federated image classification. arXiv:2106.06042. Retrieved from https:\/\/arxiv.org\/abs\/2106.06042.","journal-title":"arXiv:2106.06042"},{"key":"e_1_3_2_38_2","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","author":"Papernot Nicolas","year":"2016","unstructured":"Nicolas Papernot, Mart\u00edn Abadi, Ulfar Erlingsson, Ian Goodfellow, and Kunal Talwar. 2016. Semi-supervised knowledge transfer for deep learning from private training data. arXiv:1610.05755. Retrieved from https:\/\/arxiv.org\/abs\/1610.05755.","journal-title":"arXiv:1610.05755"},{"key":"e_1_3_2_39_2","article-title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models","author":"Salem Ahmed","year":"2018","unstructured":"Ahmed Salem, Yang Zhang, Mathias Humbert, Pascal Berrang, Mario Fritz, and Michael Backes. 2018. Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models. arXiv:1806.01246. Retrieved from https:\/\/arxiv.org\/abs\/s1806.01246.","journal-title":"arXiv:1806.01246"},{"key":"e_1_3_2_40_2","first-page":"1842","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201916)","author":"Santoro Adam","year":"2016","unstructured":"Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, and Timothy Lillicrap. 2016. Meta-learning with memory-augmented neural networks. In Proceedings of the International Conference on Machine Learning (ICML\u201916). 1842\u20131850."},{"key":"e_1_3_2_41_2","first-page":"1723","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS\u201919)","author":"Shaban Amirreza","year":"2019","unstructured":"Amirreza Shaban, Ching-An Cheng, Nathan Hatch, and Byron Boots. 2019. Truncated back-propagation for bilevel optimization. In Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS\u201919). PMLR, 1723\u20131732."},{"key":"e_1_3_2_42_2","unstructured":"Tao Shen Jie Zhang Xinkang Jia Fengda Zhang Gang Huang Pan Zhou Fei Wu and Chao Wu. 2020. Federated mutual learning. (unpublished)."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_44_2","first-page":"4424","volume-title":"Advances in Neural Information Processing Systems","author":"Smith Virginia","year":"2017","unstructured":"Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi, and Ameet S. Talwalkar. 2017. Federated multi-task learning. In Advances in Neural Information Processing Systems. 4424\u20134434."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00021"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.12.015"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"e_1_3_2_48_2","first-page":"601\u2013 618","volume-title":"Proceedings of the 25th USENIX Security Symposium (USENIX Security\u201916)","author":"Tram\u00e8r Florian","year":"2016","unstructured":"Florian Tram\u00e8r, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. 2016. Stealing machine learning models via prediction apis. In Proceedings of the 25th USENIX Security Symposium (USENIX Security\u201916). 601\u2013 618."},{"key":"e_1_3_2_49_2","first-page":"5998","volume-title":"Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201917)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Conference and Workshop on Neural Information Processing Systems (NeurIPS\u201917). 5998\u20136008."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"e_1_3_2_51_2","article-title":"Personalized federated learning for intelligent iot applications: A cloud-edge based framework","author":"Wu Qiong","year":"2020","unstructured":"Qiong Wu, Kaiwen He, and Xu Chen. 2020. Personalized federated learning for intelligent iot applications: A cloud-edge based framework. IEEE Comput. Graph. Appl. (2020).","journal-title":"IEEE Comput. Graph. Appl."},{"key":"e_1_3_2_52_2","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. (unpublished)."},{"key":"e_1_3_2_53_2","article-title":"Bayhenn: Combining bayesian deep learning and homomorphic encryption for secure dnn inference","author":"Xie Peichen","year":"2019","unstructured":"Peichen Xie, Bingzhe Wu, and Guangyu Sun. 2019. Bayhenn: Combining bayesian deep learning and homomorphic encryption for secure dnn inference. arXiv:1906.00639. Retrieved from https:\/\/arxiv.org\/abs\/1906.00639.","journal-title":"arXiv:1906.00639"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom\/BigDataSE.2019.00057"},{"key":"e_1_3_2_55_2","article-title":"Fedpd: A federated learning framework with optimal rates and adaptivity to non-iid data","author":"Zhang Xinwei","year":"2020","unstructured":"Xinwei Zhang, Mingyi Hong, Sairaj Dhople, Wotao Yin, and Yang Liu. 2020. Fedpd: A federated learning framework with optimal rates and adaptivity to non-iid data. arXiv:2005.11418. Retrieved from https:\/\/arxiv.org\/abs\/2005.11418.","journal-title":"arXiv:2005.11418"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591362","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:21Z","timestamp":1750178841000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,15]]},"references-count":54,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8,31]]}},"alternative-id":["10.1145\/3591362"],"URL":"https:\/\/doi.org\/10.1145\/3591362","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,15]]},"assertion":[{"value":"2022-06-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-27","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}