20.500.12556/RUL-185008 Label-free dataset profiling for federated client clustering Clustering clients into groups with relatively homogeneous data distributions is a key strategy for improving federated learning under non-independent and identically distributed data. However, most state-of-the-art clustering approaches require clients to possess labeled datasets and perform substantial local computation, limiting their applicability in real-world settings. To address these limitations, we introduce CoLEDS, a method for profiling unlabeled client datasets with minimal computational overhead. CoLEDS trains a model using a contrastive learning objective defined across multiple clients and optimized in a distributed fashion through joint client–server coordination. The resulting model embeds key properties of client datasets into low-dimensional vectors that are shared with the server for clustering. Extensive empirical evaluation shows that these profiles accurately capture latent dataset characteristics. By clustering clients based on these representations, CoLEDS yields federatively trained models that are better aligned with individual data distributions and enables appropriate model assignment even for clients that do not participate in federated training federated learning dataset profiling data non-IIDness client clustering zvezno učenje profiliranje podatkovne množice gručenje klientov true false true Angleški jezik Slovenski jezik Članek v reviji 2026-07-20 13:42:20 2026-07-20 13:42:21 2026-07-21 04:02:46 0000-00-00 00:00:00 2026 0 0 36 str. iss. 5, art. 72 Vol. 40 Oct. 2026 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85:004.75 1384-5810 10.1007/s10618-026-01240-9 285152771 RAZ_Radovic_Boris_2026.pdf RAZ_Radovic_Boris_2026.pdf 1 5DCD282C6ACE11FE26505529B780A1C6 5efe4b3acae1ecbab5b37274450254d9ae3da293a3b287d45d38c81b11b1f350 6610f48d-8430-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=240496 https://link.springer.com/article/10.1007/s10618-026-01240-9 1 d767fee5-842f-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=240495 Fakulteta za računalništvo in informatiko 0 0 0