Label-free dataset profiling for federated client clustering

Radovič, Boris (author), Canini, Marco (author), Pejović, Veljko (author)

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

• Language: English
• Keywords: federated learning, dataset profiling, data non-IIDness, client clustering
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: 36 str.
• Numbering: Vol. 40, iss. 5, art. 72
• PID: 20.500.12556/RUL-185008
• UDC: 004.85:004.75
• ISSN on article: 1384-5810
• DOI: 10.1007/s10618-026-01240-9
• COBISS.SI-ID: 285152771
• Publication date in RUL: 20.07.2026

Record is a part of a journal

• Title: Data mining and knowledge discovery
• Publisher: Springer Nature
• ISSN: 1384-5810
• COBISS.SI-ID: 14278183

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: zvezno učenje, profiliranje podatkovne množice, gručenje klientov

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: J2-3047-2021
• Name: Kontekstno-odvisno približno računanje na mobilnih napravah

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: N2-0393-2025
• Name: Približno računanje za prilagodljivo porazdeljeno umetno inteligenco