Heterogeneous Graph Neural Network on Semantic Tree

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Guan, Mingyu, Stokes, Jack W., Luo, Qinlong, Liu, Fuchen, Mehta, Purvanshi, Nouri, Elnaz, Kim, Taesoo
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917982716821504
author Guan, Mingyu
Stokes, Jack W.
Luo, Qinlong
Liu, Fuchen
Mehta, Purvanshi
Nouri, Elnaz
Kim, Taesoo
author_facet Guan, Mingyu
Stokes, Jack W.
Luo, Qinlong
Liu, Fuchen
Mehta, Purvanshi
Nouri, Elnaz
Kim, Taesoo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13496
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Heterogeneous Graph Neural Network on Semantic Tree
Guan, Mingyu
Stokes, Jack W.
Luo, Qinlong
Liu, Fuchen
Mehta, Purvanshi
Nouri, Elnaz
Kim, Taesoo
Machine Learning
Social and Information Networks
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.
title Heterogeneous Graph Neural Network on Semantic Tree
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2402.13496