RAC-DMVC: Reliability-Aware Contrastive Deep Multi-View Clustering under Multi-Source Noise

2025-11-17

AI Summary

To address performance degradation in multi-view clustering under heterogeneous noise—specifically missing and observational noise—this paper proposes the Reliability-Aware Contrastive Deep Multi-View Clustering (RAC-DMVC) framework. RAC-DMVC constructs a reliability-guided graph to steer robust representation learning, integrating cross-view reconstruction, a dual-attention mechanism (jointly modeling view-shared and view-specific characteristics), and self-supervised cluster distillation. Crucially, it introduces reliability-aware contrastive learning to mitigate bias in positive/negative sample selection induced by noise. Extensive experiments on five benchmark datasets demonstrate that RAC-DMVC consistently outperforms state-of-the-art methods across diverse noise ratios, exhibiting superior robustness and generalization. The framework establishes a novel paradigm for unsupervised multi-view clustering in complex, noisy environments.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Multi-view clustering (MVC), which aims to separate the multi-view data into distinct clusters in an unsupervised manner, is a fundamental yet challenging task. To enhance its applicability in real-world scenarios, this paper addresses a more challenging task: MVC under multi-source noises, including missing noise and observation noise. To this end, we propose a novel framework, Reliability-Aware Contrastive Deep Multi-View Clustering (RAC-DMVC), which constructs a reliability graph to guide robust representation learning under noisy environments. Specifically, to address observation noise, we introduce a cross-view reconstruction to enhances robustness at the data level, and a reliability-aware noise contrastive learning to mitigates bias in positive and negative pairs selection caused by noisy representations. To handle missing noise, we design a dual-attention imputation to capture shared information across views while preserving view-specific features. In addition, a self-supervised cluster distillation module further refines the learned representations and improves the clustering performance. Extensive experiments on five benchmark datasets demonstrate that RAC-DMVC outperforms SOTA methods on multiple evaluation metrics and maintains excellent performance under varying ratios of noise.

Problem

• Addresses multi-view clustering under missing and observation noise
• Proposes reliability-aware contrastive learning for robust representation
• Handles noise through cross-view reconstruction and dual-attention imputation

Innovation

• Reliability graph guides robust representation learning
• Cross-view reconstruction enhances data-level noise robustness
• Dual-attention imputation handles missing data across views