Structure fusion based on graph convolutional networks for semi-supervised classification

Abstract

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.

References in corpus (15)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Spectral Networks and Locally Connected Networks on Graphs
• Large-Scale Learnable Graph Convolutional Networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks
• Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• On Filter Size in Graph Convolutional Networks
• Transfer feature generating networks with semantic classes structure for zero-shot learning
• Class label autoencoder for zero-shot learning
• Structure propagation for zero-shot learning
• Semi-supervised Learning on Graph with an Alternating Diffusion Process

Cited by in corpus (2)

• Graph Neural Distance Metric Learning with Graph-Bert
• Deep graph learning for semi-supervised classification