multi-viewgraphclustering, which seeks a partition of the graph with multiple views that often provide more comprehensive yet complex information, has received considerable attention in recent years. Although some e...
详细信息
ISBN:
(纸本)9781450370233
multi-viewgraphclustering, which seeks a partition of the graph with multiple views that often provide more comprehensive yet complex information, has received considerable attention in recent years. Although some efforts have been made for multi-viewgraphclustering and achieve decent performances, most of them employ shallow model to deal with the complex relation within multi-viewgraph, which may seriously restrict the capacity for modeling multi-viewgraph information. In this paper, we make the first attempt to employ deep learning technique for attributed multi-view graph clustering, and propose a novel task-guided One2multigraph autoencoder clustering framework. The One2multigraph autoencoder is able to learn node embeddings by employing one informative graphview and content data to reconstruct multiple graphviews. Hence, the shared feature representation of multiple graphs can be well captured. Furthermore, a self-training clustering objective is proposed to iteratively improve the clustering results. By integrating the self-training and autoencoder's reconstruction into a unified framework, our model can jointly optimize the cluster label assignments and embeddings suitable for graphclustering. Experiments on real-world attributedmulti-viewgraph datasets well validate the effectiveness of our model.
暂无评论