Graph Laplacian Regularized Graph Convolutional Networks for Semi-supervised Learning
This work addresses a limitation in GCNs for semi-supervised classification, offering a domain-specific improvement for graph data representation.
The authors tackled the problem of graph convolutional networks (GCNs) not incorporating local invariance constraints for semi-supervised learning on graph-structured data, and they introduced a graph Laplacian GCN (gLGCN) that improved performance, as shown in experiments.
Recently, graph convolutional network (GCN) has been widely used for semi-supervised classification and deep feature representation on graph-structured data. However, existing GCN generally fails to consider the local invariance constraint in learning and representation process. That is, if two data points Xi and Xj are close in the intrinsic geometry of the data distribution, then their labels/representations should also be close to each other. This is known as local invariance assumption which plays an essential role in the development of various kinds of traditional algorithms, such as dimensionality reduction and semi-supervised learning, in machine learning area. To overcome this limitation, we introduce a graph Laplacian GCN (gLGCN) approach for graph data representation and semi-supervised classification. The proposed gLGCN model is capable of encoding both graph structure and node features together while maintains the local invariance constraint naturally for robust data representation and semi-supervised classification. Experiments show the benefit of the benefits the proposed gLGCN network.