Attributed Graph Clustering via Adaptive Graph Convolution

TL;DR

This paper introduces an adaptive high-order graph convolution approach for attributed graph clustering, effectively capturing global structures and improving performance over existing methods.

Contribution

It proposes a novel adaptive graph convolution technique that dynamically selects the optimal convolution order for different graphs, enhancing clustering results.

Findings

Outperforms state-of-the-art clustering methods on benchmark datasets

Theoretically validated the effectiveness of high-order graph convolution

Adaptive selection of convolution order improves clustering accuracy

Abstract

Attributed graph clustering is challenging as it requires joint modelling of graph structures and node attributes. Recent progress on graph convolutional networks has proved that graph convolution is effective in combining structural and content information, and several recent methods based on it have achieved promising clustering performance on some real attributed networks. However, there is limited understanding of how graph convolution affects clustering performance and how to properly use it to optimize performance for different graphs. Existing methods essentially use graph convolution of a fixed and low order that only takes into account neighbours within a few hops of each node, which underutilizes node relations and ignores the diversity of graphs. In this paper, we propose an adaptive graph convolution method for attributed graph clustering that exploits high-order graph convolution to capture global cluster structure and adaptively selects the appropriate order for different graphs. We establish the validity of our method by theoretical analysis and extensive experiments on benchmark datasets. Empirical results show that our method compares favourably with state-of-the-art methods.