Generative Diffusion Contrastive Network for Multi-View Clustering

2025-09-11

AI Summary

To address degraded fusion quality in multi-view clustering (MVC) caused by view-wise noise corruption and missing views, this paper proposes the Stochastic Generative Diffusion Fusion (SGDF) method and the Generative Diffusion Contrastive Network (GDCN). SGDF models view uncertainty via a stochastic generative mechanism coupled with a diffusion process, effectively mitigating the adverse effects of noise and incompleteness. GDCN integrates a multi-generator architecture into a contrastive learning framework to enhance cross-view feature robustness and discriminability. Evaluated on multiple standard benchmarks, the proposed approach achieves state-of-the-art clustering performance, demonstrating superior adaptability to incomplete and noisy multi-view data. The source code is publicly available.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In recent years, Multi-View Clustering (MVC) has been significantly advanced under the influence of deep learning. By integrating heterogeneous data from multiple views, MVC enhances clustering analysis, making multi-view fusion critical to clustering performance. However, there is a problem of low-quality data in multi-view fusion. This problem primarily arises from two reasons: 1) Certain views are contaminated by noisy data. 2) Some views suffer from missing data. This paper proposes a novel Stochastic Generative Diffusion Fusion (SGDF) method to address this problem. SGDF leverages a multiple generative mechanism for the multi-view feature of each sample. It is robust to low-quality data. Building on SGDF, we further present the Generative Diffusion Contrastive Network (GDCN). Extensive experiments show that GDCN achieves the state-of-the-art results in deep MVC tasks. The source code is publicly available at https://github.com/HackerHyper/GDCN.

Problem

• Addressing low-quality data in multi-view clustering
• Handling noisy and missing data across views
• Improving multi-view fusion robustness with generative diffusion

Innovation

• Stochastic Generative Diffusion Fusion method
• Multiple generative mechanism for features
• Robust to noisy and missing data