Learning the Implicit Semantic Representation on Graph-Structured Data
This addresses the challenge of capturing complex interactions in graphs for machine learning applications, but it is incremental as it builds on existing graph convolutional network methods.
The paper tackles the problem of unexploited implicit semantic associations in graph-structured data by proposing Semantic Graph Convolutional Networks (SGCN), which learns latent semantic-paths dynamically and automatically, achieving superior performance on standard datasets.
Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while the implicit semantic associations behind highly complex interactions of graphs are largely unexploited. In this paper, we propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs. In previous work, there are explorations of graph semantics via meta-paths. However, these methods mainly rely on explicit heterogeneous information that is hard to be obtained in a large amount of graph-structured data. SGCN first breaks through this restriction via leveraging the semantic-paths dynamically and automatically during the node aggregating process. To evaluate our idea, we conduct sufficient experiments on several standard datasets, and the empirical results show the superior performance of our model.