Attention-driven Graph Clustering Network

TL;DR

The paper introduces AGCN, a deep clustering network that adaptively fuses node features and multi-scale graph information using attention mechanisms, leading to improved clustering performance.

Contribution

It proposes a novel attention-driven fusion framework for deep graph clustering, effectively combining features at different scales and types for better discriminative representations.

Findings

AGCN outperforms state-of-the-art clustering methods on benchmark datasets.

The heterogeneity-wise and scale-wise fusion modules enhance feature representation.

The method achieves superior clustering accuracy and robustness.

Abstract

The combination of the traditional convolutional network (i.e., an auto-encoder) and the graph convolutional network has attracted much attention in clustering, in which the auto-encoder extracts the node attribute feature and the graph convolutional network captures the topological graph feature. However, the existing works (i) lack a flexible combination mechanism to adaptively fuse those two kinds of features for learning the discriminative representation and (ii) overlook the multi-scale information embedded at different layers for subsequent cluster assignment, leading to inferior clustering results. To this end, we propose a novel deep clustering method named Attention-driven Graph Clustering Network (AGCN). Specifically, AGCN exploits a heterogeneity-wise fusion module to dynamically fuse the node attribute feature and the topological graph feature. Moreover, AGCN develops a scale-wise fusion module to adaptively aggregate the multi-scale features embedded at different layers. Based on a unified optimization framework, AGCN can jointly perform feature learning and cluster assignment in an unsupervised fashion. Compared with the existing deep clustering methods, our method is more flexible and effective since it comprehensively considers the numerous and discriminative information embedded in the network and directly produces the clustering results. Extensive quantitative and qualitative results on commonly used benchmark datasets validate that our AGCN consistently outperforms state-of-the-art methods.