Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data

Wang, Jiazhen; Chen, Xinyue; Liu, Shuaiyu; He, Zican; Ren, Yazhou; Wang, Yi; Xia, Shuyin

doi:10.24963/ijcai.2026/551

Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data

Jiazhen Wang, Xinyue Chen, Shuaiyu Liu, Zican He, Yazhou Ren, Yi Wang, Shuyin Xia

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 4949-4957.

https://doi.org/10.24963/ijcai.2026/551

Keywords

Machine Learning: Clustering
Machine Learning: Federated learning
Machine Learning: Multi-view learning

Abstract

Federated multi-view clustering (FedMVC) has been widely used to discover latent structures in distributed multi-view data, yet most methods still rely on the restrictive assumption of independent and identically distributed (IID) data. In practice, non-IID distributions with partial and imbalanced categories cause clients to learn biased and local representations, leading to model bias and unstable federated training performance. To address these issues, we propose a FedMVC framework called Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering under Non-IID Data (H²-FedMVC), which tackles both inter-view and client heterogeneity in mixed-view settings. We propose a leader-guided learning mechanism to address inter-view heterogeneity by enhancing complementary and discriminative feature learning, and an expert adaptive aggregation strategy to handle client heterogeneity by prioritizing well-matched experts in global updates. Theoretical analysis and experiments demonstrate superior performance in heterogeneous mixed-view FedMVC settings, with code provided at https://github.com/JiazhenWang-0522/H2-FedMVC.

Jiazhen Wang, Xinyue Chen, Shuaiyu Liu, Zican He, Yazhou Ren, Yi Wang, and Shuyin Xia. 2026. Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 4949–4957. https://doi.org/10.24963/ijcai.2026/551

@inproceedings{ijcai2026p551,
  title     = {Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data},
  author    = {Wang, Jiazhen and Chen, Xinyue and Liu, Shuaiyu and He, Zican and Ren, Yazhou and Wang, Yi and Xia, Shuyin},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {4949--4957},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/551},
  url       = {https://doi.org/10.24963/ijcai.2026/551},
}

TY  - CPAPER
TI  - Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data
AU  - Wang, Jiazhen
AU  - Chen, Xinyue
AU  - Liu, Shuaiyu
AU  - He, Zican
AU  - Ren, Yazhou
AU  - Wang, Yi
AU  - Xia, Shuyin
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 4949
EP  - 4957
DO  - 10.24963/ijcai.2026/551
UR  - https://doi.org/10.24963/ijcai.2026/551
ER  -