---
title: "Bridging Inter-View and Client Heterogeneity: Federated Multi-View Clustering Under Non-IID Data"
authors:
  - "Jiazhen Wang"
  - "Xinyue Chen"
  - "Shuaiyu Liu"
  - "Zican He"
  - "Yazhou Ren"
  - "Yi Wang"
  - "Shuyin Xia"
doi: "10.24963/ijcai.2026/551"
url: "https://ijcai.org/proceedings/2026/551"
pdf: "https://ijcai.org/proceedings/2026/0551.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "4949-4957"
track: "Main Track"
keywords:
  - "Machine Learning: Clustering"
  - "Machine Learning: Federated learning"
  - "Machine Learning: Multi-view learning"
---

# 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

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 4949-4957. DOI: [10.24963/ijcai.2026/551](https://doi.org/10.24963/ijcai.2026/551)

## 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.