Structure fusion based on graph convolutional networks for semi-supervised classification
This work addresses semi-supervised classification for multi-view data, which is an incremental improvement over existing graph convolutional networks by incorporating structure fusion.
The paper tackled the problem of semi-supervised classification with multi-view data by proposing a structure fusion method based on graph convolutional networks (SF-GCN) to capture both specific and common structures, resulting in improved performance that outperforms state-of-the-art methods on three citation network datasets (Cora, Citeseer, Pubmed).
Suffering from the multi-view data diversity and complexity for semi-supervised classification, most of existing graph convolutional networks focus on the networks architecture construction or the salient graph structure preservation, and ignore the the complete graph structure for semi-supervised classification contribution. To mine the more complete distribution structure from multi-view data with the consideration of the specificity and the commonality, we propose structure fusion based on graph convolutional networks (SF-GCN) for improving the performance of semi-supervised classification. SF-GCN can not only retain the special characteristic of each view data by spectral embedding, but also capture the common style of multi-view data by distance metric between multi-graph structures. Suppose the linear relationship between multi-graph structures, we can construct the optimization function of structure fusion model by balancing the specificity loss and the commonality loss. By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as adjacent matrix to input graph convolutional networks for semi-supervised classification. Experiments demonstrate that the performance of SF-GCN outperforms that of the state of the arts on three challenging datasets, which are Cora,Citeseer and Pubmed in citation networks.