{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T15:30:58Z","timestamp":1775662258793,"version":"3.50.1"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"UL\/SnT\u2013ILNAS on Technical Standardisation for Trustworthy ICT, Aerospace, and Construction"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Model. Perform. Eval. Comput. Syst."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>The Federated Learning paradigm is a distributed machine learning strategy, developed for settings where training data is owned by distributed devices and cannot be shared with others. Federated Learning circumvents this constraint by carrying out model training in distribution, so that each participant, or client, trains a local model only on its own data. The parameters of these local models are shared intermittently among participants and aggregated to enhance model accuracy. This strategy has shown impressive success, and has been rapidly adopted by the industry in efforts to overcome confidentiality and resource constraints in model training.<\/jats:p>\n          <jats:p>\n            However, the application of FL to real-world settings brings additional challenges, many associated with heterogeneity between participants. Research into mitigating these difficulties in Federated Learning has largely focused on only two particular types of heterogeneity: the unbalanced distribution of training data, and differences in client resources. Yet many more types of heterogeneity exist, and some are becoming increasingly relevant as the capability of FL expands to cover more and more complex real-world problems, from the tuning of large language models to enabling machine learning on edge devices. In this work, we discuss a novel type of heterogeneity that is likely to become increasingly relevant in future applications: this is\n            <jats:italic>preference heterogeneity<\/jats:italic>\n            , emerging when clients learn under multiple objectives, with different importance assigned to each objective on different clients.\n          <\/jats:p>\n          <jats:p>In this work, we discuss the implications of this type of heterogeneity and propose a FedPref, a first algorithm designed to facilitate personalised federated learning in this setting. We demonstrate the effectiveness of the algorithm across several different problems, preference distributions and model architectures. In addition, we introduce a new analytical point of view, based on multi-objective metrics, for evaluating the performance of federated algorithms in this setting beyond the traditional client-focused metrics. We perform a second experimental analysis based in this view, and show that FedPref outperforms compared algorithms.<\/jats:p>","DOI":"10.1145\/3708984","type":"journal-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T10:07:23Z","timestamp":1734689243000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["FedPref: Federated Learning Across Heterogeneous Multi-objective Preferences"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-3703","authenticated-orcid":false,"given":"Maria","family":"Hartmann","sequence":"first","affiliation":[{"name":"SnT, University of Luxembourg, Esch-sur-Alzette, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9419-4210","authenticated-orcid":false,"given":"Gr\u00e9goire","family":"Danoy","sequence":"additional","affiliation":[{"name":"FSTM\/DCS, SnT, University of Luxembourg, Esch-sur-Alzette, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9338-2834","authenticated-orcid":false,"given":"Pascal","family":"Bouvry","sequence":"additional","affiliation":[{"name":"FSTM\/DCS, University of Luxembourg, Esch-sur-Alzette, Luxembourg"}]}],"member":"320","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2023.3250275"},{"key":"e_1_3_4_3_2","unstructured":"Axel Abels Diederik M. Roijers Tom Lenaerts Ann Now\u00e9 and Denis Steckelmacher. 2019. Dynamic weights in multi-objective deep reinforcement learning. Proceedings of the 36th International Conference on Machine Learning. Available from https:\/\/proceedings.mlr.press\/v97\/abels19a.html"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2981430"},{"key":"e_1_3_4_5_2","first-page":"5037","volume-title":"Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Cai Ruisi","year":"2023","unstructured":"Ruisi Cai, Xiaohan Chen, Shiwei Liu, Jayanth Srinivasa, Myungjin Lee, Ramana Kompella, and Zhangyang Wang. 2023. Many-task federated learning: A new problem setting and a simple baseline. In Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. IEEE, Canada, 5037\u20135045. DOI:10.1109\/cvprw59228.2023.00532"},{"key":"e_1_3_4_6_2","first-page":"7871","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Che Tianshi","year":"2023","unstructured":"Tianshi Che, Ji Liu, Yang Zhou, Jiaxiang Ren, Jiwen Zhou, Victor Sheng, Huaiyu Dai, and Dejing Dou. 2023. Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.Houda Bouamor, Juan Pino, and Kalika Bali (Eds.), Association for Computational Linguistics, Singapore, 7871\u20137888. DOI:10.18653\/v1\/2023.emnlp-main.488"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-005-6164-x"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iay008"},{"key":"e_1_3_4_9_2","first-page":"228","volume-title":"Proceedings of the 2021 IEEE Intl Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking. IEEE Computer Society","author":"Duan Moming","year":"2021","unstructured":"Moming Duan, Duo Liu, Xinyuan Ji, Renping Liu, Liang Liang, Xianzhang Chen, and Yujuan Tan. 2021. FedGroup: Efficient federated learning via decomposed similarity-based clustering. In Proceedings of the 2021 IEEE Intl Conf on Parallel and Distributed Processing with Applications, Big Data and Cloud Computing, Sustainable Computing and Communications, Social Computing and Networking. IEEE Computer Society, Los Alamitos, CA, USA, 228\u2013237. DOI:10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00042"},{"key":"e_1_3_4_10_2","first-page":"30","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Felten Florian","year":"2024","unstructured":"Florian Felten, Lucas N. Alegre, Ann Now\u00e9, Ana L. C. Bazzan, El-Ghazali Talbi, Gr\u00e9goire Danoy, and Bruno C. da Silva. 2024. A toolkit for reliable benchmarking and research in multi-objective reinforcement learning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) Curran Associates Inc., Red Hook, NY, USA, 30 pages."},{"key":"e_1_3_4_11_2","first-page":"12","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Ghosh Avishek","year":"2020","unstructured":"Avishek Ghosh, Jichan Chung, Dong Yin, and Kannan Ramchandran. 2020. An efficient framework for clustered federated learning. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada). Curran Associates Inc., Red Hook, NY, USA, 12 pages."},{"key":"e_1_3_4_12_2","first-page":"1","volume-title":"Proceedings of the International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023","author":"Hartmann Maria","year":"2023","unstructured":"Maria Hartmann, Gr\u00e9goire Danoy, Mohammed Alswaitti, and Pascal Bouvry. 2023. MOFL\/D: A federated multi-objective learning framework with decomposition. In Proceedings of the International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023 (New Orleans, LA, USA). International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023, New Orleans, LA, USA, 1\u201313. Retrieved from https:\/\/openreview.net\/forum?id=Pj6BPHZy56"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3169117"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/tbme.2022.3210940"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_3_4_16_2","series-title":"Proceedings of Machine Learning Research","first-page":"5132","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. 2020. SCAFFOLD: Stochastic controlled averaging for federated learning. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 119).Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 5132\u20135143. Retrieved from https:\/\/proceedings.mlr.press\/v119\/karimireddy20a.html"},{"key":"e_1_3_4_17_2","first-page":"10708","volume-title":"Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li Q.","year":"2021","unstructured":"Q. Li, B. He, and D. Song. 2021. Model-contrastive federated learning. In Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, Los Alamitos, CA, USA, 10708\u201310717. DOI:10.1109\/CVPR46437.2021.01057"},{"key":"e_1_3_4_18_2","unstructured":"Tian Li Anit Kumar Sahu Manzil Zaheer Maziar Sanjabi Ameet Talwalkar Virginia Smith. 2020. Federated optimization in heterogeneous networks. MLSys 2020."},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-022-01046-x"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2201.09917"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_4_22_2","first-page":"84\u2013 91","volume-title":"Proceedings of the 13th International Conference on, Intelligent Systems Application to Power SystemsProceedings of the 13th International Conference on Intelligent Systems Application to Power Systems.","author":"Ngatchou P.","year":"2005","unstructured":"P. Ngatchou, Anahita Zarei, and A. El-Sharkawi. 2005. Pareto multi objective optimization, In Proceedings of the 13th International Conference on, Intelligent Systems Application to Power Systems. Proceedings of the 13th International Conference on Intelligent Systems Application to Power Systems. 84\u2013 91. DOI:10.1109\/ISAP.2005.1599245"},{"key":"e_1_3_4_23_2","first-page":"1","volume-title":"Proceedings of the 2015 Latin American Computing Conference","author":"Riquelme Nery","year":"2015","unstructured":"Nery Riquelme, Christian Von Lucken, and Benjamin Baran. 2015. Performance metrics in multi-objective optimization. In Proceedings of the 2015 Latin American Computing Conference. IEEE, Arequipa, Peru, 1\u201311. DOI:10.1109\/clei.2015.7360024"},{"key":"e_1_3_4_24_2","doi-asserted-by":"crossref","first-page":"3710","DOI":"10.1109\/TNNLS.2020.3015958","article-title":"Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints","volume":"32","author":"Sattler Felix","year":"2019","unstructured":"Felix Sattler, Klaus-Robert M\u00fcller, and Wojciech Samek. 2019. Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints. IEEE Transactions on Neural Networks and Learning Systems 32, ISSN 2162-2388 (2019), 3710\u20133722. Retrieved from https:\/\/api.semanticscholar.org\/CorpusID:203736521","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-022-09778-9"},{"key":"e_1_3_4_26_2","first-page":"4427","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Smith Virginia","year":"2017","unstructured":"Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi, and Ameet Talwalkar. 2017. Federated multi-task learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA). Curran Associates Inc., Red Hook, NY, USA, 4427\u20134437."},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3160699"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1145\/3560442.3560445","volume-title":"Proceedings of the 2022 6th High Performance Computing and Cluster Technologies Conference","author":"Varrette Sebastien","year":"2022","unstructured":"Sebastien Varrette, Hyacinthe Cartiaux, Sarah Peter, Emmanuel Kieffer, Teddy Valette, and Abatcha Olloh. 2022. Management of an academic HPC and research computing facility: The ULHPC experience 2.0. In Proceedings of the 2022 6th High Performance Computing and Cluster Technologies Conference (Fuzhou, China). Association for Computing Machinery, New York, NY, USA, 14\u201324. DOI:10.1145\/3560442.3560445"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","unstructured":"Kangkang Wang Rajiv Mathews Chlo\u00e9 Kiddon Hubert Eichner Fran\u00e7oise Beaufays and Daniel Ramage. 2019. Federated Evaluation of On-device Personalization. ArXiv preprint. DOI:10.48550\/ARXIV.1910.10252","DOI":"10.48550\/ARXIV.1910.10252"},{"key":"e_1_3_4_31_2","series-title":"Proceedings of Machine Learning Research","first-page":"10607","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Xu Jie","year":"2020","unstructured":"Jie Xu, Yunsheng Tian, Pingchuan Ma, Daniela Rus, Shinjiro Sueda, and Wojciech Matusik. 2020. Prediction-guided multi-objective reinforcement learning for continuous robot control. In Proceedings of the 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 119).Hal Daum\u00e9 III and Aarti Singh (Eds.), PMLR, 10607\u201310616. Retrieved from https:\/\/proceedings.mlr.press\/v119\/xu20h.html"},{"key":"e_1_3_4_32_2","first-page":"39602","volume-title":"Proceedings of the Advances in Neural Information Processing Systems.","volume":"36","author":"Yang Haibo","year":"2023","unstructured":"Haibo Yang, Zhuqing Liu, Jia Liu, Chaosheng Dong, and Michinari Momma. 2023. Federated multi-objective learning. In Proceedings of the Advances in Neural Information Processing Systems.A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36, Curran Associates, Inc., Red Hook, NY, USA, 39602\u201339625. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/7cb2c2a8d35576c00078b6591ec26a7d-Paper-Conference.pdf"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3625558"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","unstructured":"Binhang Yuan Song Ge and Wenhui Xing. 2020. A federated learning framework for healthcare IoT devices. ArXiv preprint. DOI:10.48550\/arXiv.2005.05083","DOI":"10.48550\/arXiv.2005.05083"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx105"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919699"},{"key":"e_1_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.098"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/4235.797969"}],"container-title":["ACM Transactions on Modeling and Performance Evaluation of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708984","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708984"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3708984"],"URL":"https:\/\/doi.org\/10.1145\/3708984","relation":{},"ISSN":["2376-3639","2376-3647"],"issn-type":[{"value":"2376-3639","type":"print"},{"value":"2376-3647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]},"assertion":[{"value":"2024-04-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}