Heterogeneous Graph Transformer for Meta-structure Learning with Application in Text Classification
-
Published:2023-05-22
Issue:3
Volume:17
Page:1-27
-
ISSN:1559-1131
-
Container-title:ACM Transactions on the Web
-
language:en
-
Short-container-title:ACM Trans. Web
Author:
Wang Shuhai1ORCID,
Liu Xin1ORCID,
Pan Xiao1ORCID,
Xu Hanjie2ORCID,
Liu Mingrui1ORCID
Affiliation:
1. School of Information Science and Technology, Shijiazhuang Tiedao University
2. McMaster University
Abstract
The prevalent heterogeneous Graph Neural Network (GNN) models learn node and graph representations using pre-defined meta-paths or only automatically discovering meta-paths. However, the existing methods suffer from information loss due to neglecting undiscovered meta-structures with richer semantics than meta-paths in heterogeneous graphs. To take advantage of the current rich meta-structures in heterogeneous graphs, we propose a novel approach called HeGTM to automatically extract essential meta-structures (i.e., meta-paths and meta-graphs) from heterogeneous graphs. The discovered meta-structures can capture more prosperous relations between different types of nodes that can help the model to learn representations. Furthermore, we apply the proposed approach for text classification. Specifically, we first design a heterogeneous graph for the text corpus, and then apply HeGTM on the constructed text graph to learn better text representations that contain various semantic relations. In addition, our approach can also be used as a strong meta-structure extractor for other GNN models. In other words, the auto-discovered meta-structures can replace the pre-defined meta-paths. The experimental results on text classification demonstrate the effectiveness of our approach to automatically extracting informative meta-structures from heterogeneous graphs and its usefulness in acting as a meta-structure extractor for boosting other GNN models.
Funder
S & T Program of Hebei
Natural Science Foundation of Hebei Province
Outstanding Youth Foundation of Hebei Education Department
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications
Reference107 articles.
1. Introduction to Graph Neural Networks
2. Xien Liu, Xinxin You, Xiao Zhang, Ji Wu, and Ping Lv. 2020. Tensor graph convolutional networks for text classification. In Proceedings of the AAAI. 8409–8416.
3. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the ICLR.
4. Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In Proceedings of the NeurIPS. 5171–5181.