Learning Disentangled Representations for Generalized Multi-view Clustering

TL;DR

This paper introduces GMAE, a novel auto-encoder framework that learns disentangled, view-specific and shared representations to improve multi-view clustering performance, especially on incomplete data.

Contribution

GMAE employs dual-path autoencoders and adversarial discriminators to disentangle view-specific and common features, enhancing clustering quality in multi-view data.

Findings

GMAE outperforms state-of-the-art methods on 13 benchmark datasets.

It effectively handles incomplete multi-view clustering tasks.

Disentangled representations improve clustering clarity.

Abstract

Multi-View Clustering (MVC) has gained significant attention for its ability to leverage complementary information across diverse views. However, existing deep MVC methods often struggle with view-distribution entanglement during cross-view fusion, which hampers the quality of the shared latent space and leads to suboptimal Figures. To address this issue, we propose the Generalized Multi-view Auto-Encoder (GMAE), a framework designed to preserve cross-view complementarity through disentangled representation learning. Specifically, GMAE employs dual-path autoencoders to decouple source features into view-specific and view-common embeddings, facilitating the discovery of clearer clustering structures. We further construct cross-view adversarial discriminators to guide view-specific encoders in capturing more discriminative features. By strategically modulating mutual information, GMAE effectively aligns distributions and prevents representation collapse, ensuring the generation of robust, non-trivial embeddings. Comprehensive experiments on 13 benchmark datasets demonstrate that GMAE consistently outperforms state-of-the-art methods in both complete and incomplete MVC tasks. Our code implementation is available at the repository: https://github.com/obananas/GMAE.