Heterogeneous Graph Neural Network on Semantic Tree
This addresses the challenge of handling heterogeneous graphs with hierarchical metapaths for applications like citation or email graphs, representing an incremental improvement over existing methods.
The paper tackles the problem of modeling heterogeneous graphs by introducing HetTree, a Heterogeneous Graph Neural Network that incorporates a semantic tree hierarchy among metapaths, resulting in outperforming existing baselines on benchmarks and scaling efficiently to large graphs with millions of nodes and edges.
The recent past has seen an increasing interest in Heterogeneous Graph Neural Networks (HGNNs), since many real-world graphs are heterogeneous in nature, from citation graphs to email graphs. However, existing methods ignore a tree hierarchy among metapaths, naturally constituted by different node types and relation types. In this paper, we present HetTree, a novel HGNN that models both the graph structure and heterogeneous aspects in a scalable and effective manner. Specifically, HetTree builds a semantic tree data structure to capture the hierarchy among metapaths. To effectively encode the semantic tree, HetTree uses a novel subtree attention mechanism to emphasize metapaths that are more helpful in encoding parent-child relationships. Moreover, HetTree proposes carefully matching pre-computed features and labels correspondingly, constituting a complete metapath representation. Our evaluation of HetTree on a variety of real-world datasets demonstrates that it outperforms all existing baselines on open benchmarks and efficiently scales to large real-world graphs with millions of nodes and edges.