Learning the Implicit Semantic Representation on Graph-Structured Data

Abstract

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. 4

Estimating Fund-Raising Performance for Start-up Projects from a Market Graph Perspective

“…For recommendation systems, many works utilized graph neural networks to capture the interest similarities among quite a number of customers or the content coherences of every item pair [30,31,32]. For social network modeling, the community event discovery and influence propagation were learned by designed GNNs [33,34,35]. For P2P lending, the loan requirements and investing lenders can also be matched by hybrid GCN [32].…”