{"date_created":"2026-02-10T08:20:59Z","type":"preprint","department":[{"_id":"ChLa"}],"_id":"21207","publication":"arXiv","oa":1,"tmp":{"name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png"},"year":"2025","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","OA_place":"repository","language":[{"iso":"eng"}],"doi":"10.48550/ARXIV.2505.15579","publication_status":"draft","day":"21","related_material":{"record":[{"id":"21198","status":"public","relation":"dissertation_contains"}]},"citation":{"apa":"Zakerinia, H., Scott, J. A., &#38; Lampert, C. (n.d.). Federated learning with unlabeled clients: Personalization can happen in low dimensions. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/ARXIV.2505.15579\">https://doi.org/10.48550/ARXIV.2505.15579</a>","short":"H. Zakerinia, J.A. Scott, C. Lampert, ArXiv (n.d.).","mla":"Zakerinia, Hossein, et al. “Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions.” <i>ArXiv</i>, doi:<a href=\"https://doi.org/10.48550/ARXIV.2505.15579\">10.48550/ARXIV.2505.15579</a>.","ama":"Zakerinia H, Scott JA, Lampert C. Federated learning with unlabeled clients: Personalization can happen in low dimensions. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/ARXIV.2505.15579\">10.48550/ARXIV.2505.15579</a>","ieee":"H. Zakerinia, J. A. Scott, and C. Lampert, “Federated learning with unlabeled clients: Personalization can happen in low dimensions,” <i>arXiv</i>. .","ista":"Zakerinia H, Scott JA, Lampert C. Federated learning with unlabeled clients: Personalization can happen in low dimensions. arXiv, <a href=\"https://doi.org/10.48550/ARXIV.2505.15579\">10.48550/ARXIV.2505.15579</a>.","chicago":"Zakerinia, Hossein, Jonathan A Scott, and Christoph Lampert. “Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/ARXIV.2505.15579\">https://doi.org/10.48550/ARXIV.2505.15579</a>."},"status":"public","abstract":[{"text":"Personalized federated learning has emerged as a popular approach to training on devices holding statistically heterogeneous data, known as clients. However, most existing approaches require a client to have labeled data for training or finetuning in order to obtain their own personalized model. In this paper we address this by proposing FLowDUP, a novel method that is able to generate a personalized model using only a forward pass with unlabeled data. The generated model parameters reside in a low-dimensional subspace, enabling efficient communication and computation. FLowDUP's learning objective is theoretically motivated by our new transductive multi-task PAC-Bayesian generalization bound, that provides performance guarantees for unlabeled clients. The objective is structured in such a way that it allows both clients with labeled data and clients with only unlabeled data to contribute to the training process. To supplement our theoretical results we carry out a thorough experimental evaluation of FLowDUP, demonstrating strong empirical performance on a range of datasets with differing sorts of statistically heterogeneous clients. Through numerous ablation studies, we test the efficacy of the individual components of the method.","lang":"eng"}],"date_updated":"2026-03-03T08:20:57Z","title":"Federated learning with unlabeled clients: Personalization can happen in low dimensions","date_published":"2025-05-21T00:00:00Z","corr_author":"1","month":"05","oa_version":"Preprint","article_processing_charge":"No","author":[{"last_name":"Zakerinia","id":"653bd8b6-f394-11eb-9cf6-c0bbf6cd78d4","first_name":"Hossein","orcid":"0009-0007-3977-6462","full_name":"Zakerinia, Hossein"},{"full_name":"Scott, Jonathan A","first_name":"Jonathan A","id":"e499926b-f6e0-11ea-865d-9c63db0031e8","last_name":"Scott"},{"id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","last_name":"Lampert","first_name":"Christoph","full_name":"Lampert, Christoph","orcid":"0000-0001-8622-7887"}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2505.15579","open_access":"1"}]}