Deep Fusion Clustering Network

TL;DR

This paper introduces DFCN, a deep clustering network that dynamically fuses graph structure and node attribute information, improving clustering accuracy by leveraging a novel fusion module and self-supervision strategies.

Contribution

The paper proposes a novel fusion mechanism and target distribution generation method for deep clustering, enhancing integration of structure and attribute information.

Findings

Outperforms state-of-the-art deep clustering methods on six datasets.

Demonstrates robustness and effectiveness of the fusion module.

Shows significant improvement in clustering accuracy.

Abstract

Deep clustering is a fundamental yet challenging task for data analysis. Recently we witness a strong tendency of combining autoencoder and graph neural networks to exploit structure information for clustering performance enhancement. However, we observe that existing literature 1) lacks a dynamic fusion mechanism to selectively integrate and refine the information of graph structure and node attributes for consensus representation learning; 2) fails to extract information from both sides for robust target distribution (i.e., "groundtruth" soft labels) generation. To tackle the above issues, we propose a Deep Fusion Clustering Network (DFCN). Specifically, in our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder for consensus representation learning. Also, a reliable target distribution generation measure and a triplet self-supervision strategy, which facilitate cross-modality information exploitation, are designed for network training. Extensive experiments on six benchmark datasets have demonstrated that the proposed DFCN consistently outperforms the state-of-the-art deep clustering methods.