Relationship Alignment for View-aware Multi-view Clustering

ICLR 2026 Conference Submission19765 Authors

Keywords: Relationship Alignment; View-Aware Contrastive Learning; Multi-View Clustering

Abstract: Multi-view clustering improves clustering performance by integrating complementary information from multiple views. However, existing methods often suffer from two limitations: i) the neglect of preserving sample neighborhood structures, which weakens the consistency of inter-sample relationships across views; and ii) inability to adaptively utilize inter-view similarity, resulting in representation conflicts and semantic degradation. To address these issues, we propose a novel framework named Relationship Alignment for View-aware Multi-view Clustering (RAV). Our approach first constructs a sample relation matrix for each view using deep features and aligns it with a global relation matrix to enhance neighborhood consistency across views. Furthermore, we introduce a view-aware adaptive weighting mechanism for label contrastive learning. This mechanism dynamically adjusts the contrastive intensity between view pairs based on the similarity of their deep features: higher similarity leads to stronger label alignment, while lower similarity reduces the weighting to prevent forcing inconsistent views into agreement. This strategy effectively promotes cluster-level semantic consistency while preserving natural inter-view relationships. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches on multiple benchmark datasets.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 19765