Heterogeneous Graph Transformer for Meta-structure Learning with Application in Text Classification
Open Access
- 22 May 2023
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on the Web
- Vol. 17 (3) , 1-27
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.Keywords
Funding Information
- S & T Program of Hebei (21340301D)
- Natural Science Foundation of Hebei Province (F2018210109)
- Outstanding Youth Foundation of Hebei Education Department (BJ2021085)
This publication has 33 references indexed in Scilit:
- Top-k similarity search in heterogeneous information networks with x-star network schemaExpert Systems with Applications, 2015
- Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks2015
- Inferring anchor links across multiple heterogeneous social networks2013
- Supervised Learning and Codebook Optimization for Bag-of-Words ModelsCognitive Computation, 2012
- CATALOGING AND CLASSIFICATION: AN INTRODUCTION. 3rd ed. Lois Mai Chan.Lanham, MD: Scarecrow Press, 2007, 580 pp., ISBN 0-8108-6000-7Technical Services Quarterly, 2008
- A hidden Markov model-based text classification of medical documentsJournal of Information Science, 2008
- Yago2007
- Neighbor-weighted K-nearest neighbor for unbalanced text corpusExpert Systems with Applications, 2005
- Long Short-Term MemoryNeural Computation, 1997
- Automatic Indexing: An Experimental InquiryJournal of the ACM, 1961