Heterogeneous Graph Neural Network on Semantic Tree
Mingyu Guan, Jack W Stokes, Qinlong Luo, Fuchen Liu, Purvanshi Mehta, Elnaz Nouri, Taesoo Kim
Abstract
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.
BibTeX
@article{Guan_Stokes_Luo_Liu_Mehta_Nouri_Kim_2025, title={Heterogeneous Graph Neural Network on Semantic Tree}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33860}, DOI={10.1609/aaai.v39i16.33860}, abstractNote={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.}, number={16}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Guan, Mingyu and Stokes, Jack W and Luo, Qinlong and Liu, Fuchen and Mehta, Purvanshi and Nouri, Elnaz and Kim, Taesoo}, year={2025}, month={Apr.}, pages={16924-16932} }