Link prediction in heterogeneous networks based on metapath projection and aggregation

A heterogeneous network, which contains multiple types of nodes and edges, is a special kind of network. Link prediction in heterogeneous networks is a consistently interesting research topic owing to its practical value in various applications. In this work, we present an end-to-end link prediction method for heterogeneous networks. By leveraging the metapath projection and semantic graph aggregation, the proposed method can learn the embeddings of node pairs from different metapaths. Specifically, the proposed method projects a heterogeneous network into multiple semantic graphs based on a number of metapaths, and then learns the embedding of a node pair from a probability subgraph extracted in each semantic graph via a graph neural network. Afterward, a semantic aggregation module is designed to combine the embeddings of the node pair obtained from multiple semantic graphs using an attention mechanism. Empirical study manifests that the accuracy of the proposed link prediction method is superior to that of the competing methods.

Automated summary

In this paper, an end-to-end link prediction method for heterogeneous networks is proposed. It leverages metapath projection and semantic graph aggregation to learn the embeddings of node pairs from different metapaths. The empirical study shows that the proposed method outperforms competing methods in terms of prediction accuracy.