Attributed Graph Clustering via Adaptive Graph Convolution
This work addresses the challenge of joint modeling in attributed graph clustering for applications like social network analysis, but it is incremental as it builds on existing graph convolution techniques.
The paper tackles the problem of attributed graph clustering by proposing an adaptive graph convolution method that exploits high-order convolutions to capture global cluster structure and adaptively selects the order for different graphs, achieving favorable performance compared to state-of-the-art methods on benchmark datasets.
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.