Semantic-guided graph neural network for heterogeneous graph embedding

Heterogeneous Graph Neural Network (HGNN) has shown a great promising in embedding complex structural and semantic information of heterogeneous graph. However, many popular HGNNs fail to capture the meaningful characteristics to distinguish heterogeneous nodes, known as the semantic confusion problem. In this paper, we hold that semantic confusion problem can be addressed by jumping knowledge toward semantics enrichment, and propose a general framework for heterogeneous graph embedding named Semantic-guided Graph Neural Network (SGNN). Here, we develop novel two-level fusion mechanisms in both node and semantic aggregation. In the node-level, we aggregate the local neighbors with jumping knowledge to learn an enhanced local representation. In the semantic-level, we maximize the common representation to extract the jumping knowledge from multiple semantics in latent space. The common representation is injected into semantic-level aggregation as jumping knowledge to guide the model to pay more attention on target semantics. In the end, the semantic confusion problem is shown to be alleviated in the two-level semantic-guided aggregation framework of SGNN through both theory and experiments. Experimental results demonstrate that SGNN gains highest results in real-world tasks. We also perform validation experiments to evaluate the effectiveness of aggregation mechanism towards semantic confusion in each level, and the results show superiority of SGNN.