Enhanced Federated Deep Multi-View Clustering under Uncertainty Scenario

TL;DR

This paper introduces EFDMVC, a federated clustering framework that effectively handles heterogeneous, incomplete, and conflicting multi-view data by aligning semantics and adaptively aggregating client updates, improving robustness across benchmarks.

Contribution

The paper proposes a novel federated multi-view clustering method that addresses view and aggregation uncertainties through semantic alignment, hierarchical contrastive fusion, and adaptive aggregation modules.

Findings

EFDMVC outperforms state-of-the-art methods on benchmark datasets.

The framework effectively mitigates semantic conflicts and view heterogeneity.

Experimental results show improved robustness and clustering accuracy.

Abstract

Traditional Federated Multi-View Clustering assumes uniform views across clients, yet practical deployments reveal heterogeneous view completeness with prevalent incomplete, redundant, or corrupted data. While recent approaches model view heterogeneity, they neglect semantic conflicts from dynamic view combinations, failing to address dual uncertainties: view uncertainty (semantic inconsistency from arbitrary view pairings) and aggregation uncertainty (divergent client updates with imbalanced contributions). To address these, we propose a novel Enhanced Federated Deep Multi-View Clustering framework: first align local semantics, hierarchical contrastive fusion within clients resolves view uncertainty by eliminating semantic conflicts; a view adaptive drift module mitigates aggregation uncertainty through global-local prototype contrast that dynamically corrects parameter deviations; and a balanced aggregation mechanism coordinates client updates. Experimental results demonstrate that EFDMVC achieves superior robustness against heterogeneous uncertain views across multiple benchmark datasets, consistently outperforming all state-of-the-art baselines in comprehensive evaluations.