{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T11:02:13Z","timestamp":1780570933560,"version":"3.54.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"34","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Prototype-based personalized federated learning methods have emerged as a promising strategy due to their ability to represent client-specific class characteristics effectively through learned class prototypes. These prototypes capture salient features of client-local data, facilitating personalized model adaptation. However, existing prototype-based aggregation strategies predominantly rely on weighted averaging, implicitly assuming prototype consistency across clients. This assumption neglects the intrinsic heterogeneity and non-independent and identically distributed (non-IID) nature of client data, compelling diverse local prototypes to align toward a singular global prototype and consequently causing significant aggregation bias. Motivated by observations from intra-class feature saliency analysis, we identify that clients inherently emphasize distinct feature regions even for the same class.  To leverage this intra-class diversity, we introduce FedIC, a novel prototype clustering and collaborative classifier optimization approach. Specifically, FedIC first clusters prototypes based on intra-class similarity to form intra-class prototype subspaces, ensuring that aggregation occurs exclusively within each cluster, thus eliminating the bias stemming from forced global unification. To further exploit the benefits of intra-cluster collaboration, we quantify the combined predictive gains of classifiers from clients within the same cluster as a function of classifier combination weights. This targeted aggregation and collaborative optimization strategy effectively circumvents the bias introduced by global alignment. Extensive experiments under various non-IID settings show that FedIC significantly outperforms existing Prototype-based and Clustered PFL Methods.<\/jats:p>","DOI":"10.1609\/aaai.v40i34.40113","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:27:32Z","timestamp":1773800852000},"page":"28795-28803","source":"Crossref","is-referenced-by-count":1,"title":["Intra-Class Unbiased Prototype Aggregation and Classifier Collaboration for Personalized Federated Learning"],"prefix":"10.1609","volume":"40","author":[{"given":"Hao","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyu","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiguang","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aikun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongchang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhi","family":"Pu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiyi","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40113\/44074","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40113\/44074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:27:33Z","timestamp":1773800853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40113"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i34.40113","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}