Multi?graph convolutional clustering network

The relationship between objects can be described from different angles. Although multiple kinds of relationships make the connections complex, they bring in more discriminative information for clustering tasks. Therefore, how to effectively fuse becomes a critical problem. In this paper, we propose novel Multi-graph Convolutional Clustering Network which deeply explores feature nodes and fuses nodes. Unlike most graph convolutional methods that only exploit single or directly graphs into unified before convolution operation, firstly build parallelled layers each learn diverse data representations, fully exploits statistics graphs. Then, designed multi-graph attention module above representations considers importance graph. Besides, proposed model completes transition graphs, reduces dependence quality enhances robustness Experimental results verify performs better than traditional single-graph clustering.