MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
This work addresses the challenge of embedding heterogeneous graphs for applications like social networks or knowledge graphs, but it is incremental as it builds on existing metapath-based methods.
The paper tackled the problem of heterogeneous graph embedding by addressing limitations in existing models that omit node content features, discard intermediate nodes, or consider only one metapath, resulting in improved prediction accuracy on node classification, clustering, and link prediction tasks across three real-world datasets.
A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations. Existing models usually define multiple metapaths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models either omit node content features, discard intermediate nodes along the metapath, or only consider one metapath. To address these three limitations, we propose a new model named Metapath Aggregated Graph Neural Network (MAGNN) to boost the final performance. Specifically, MAGNN employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metapath aggregation to combine messages from multiple metapaths. Extensive experiments on three real-world heterogeneous graph datasets for node classification, node clustering, and link prediction show that MAGNN achieves more accurate prediction results than state-of-the-art baselines.