Attributed Graph Clustering via Adaptive Graph Convolution

4 Jun 2019  ·  Xiaotong Zhang, Han Liu, Qimai Li, Xiao-Ming Wu ·

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.

PDF Abstract

Results from the Paper

Ranked #3 on Graph Clustering on Cora (NMI metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Clustering Citeseer AGC NMI 41.13 # 3
ACC 67.0 # 3
Graph Clustering Cora AGC NMI 53.68 # 3
ACC 68.92 # 3
Graph Clustering Pubmed AGC NMI 31.59 # 5
ACC 69.78 # 5