Inductive Meta-Path Learning for Schema-Complex Heterogeneous Information Networks
- 29 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 10196-10209
Abstract
Heterogeneous Information Networks (HINs) are information networks with multiple types of nodes and edges. The concept of meta-path, i.e., a sequence of entity types and relation types connecting two entities, is proposed to provide the meta-level explainable semantics for various HIN tasks. Traditionally, meta-paths are primarily used for schema-simple HINs, e.g., bibliographic networks with only a few entity types, where meta-paths are often enumerated with domain knowledge. However, the adoption of meta-paths for schema-complex HINs, such as knowledge bases (KBs) with hundreds of entity and relation types, has been limited due to the computational complexity associated with meta-path enumeration. Additionally, effectively assessing meta-paths requires enumerating relevant path instances, which adds further complexity to the meta-path learning process. To address these challenges, we propose SchemaWalk, an inductive meta-path learning framework for schema-complex HINs. We represent meta-paths with schema-level representations to support the learning of the scores of meta-paths for varying relations, mitigating the need of exhaustive path instance enumeration for each relation. Further, we design a reinforcement-learning based path-finding agent, which directly navigates the network schema (i.e., schema graph) to learn policies for establishing meta-paths with high coverage and confidence for multiple relations. Extensive experiments on real data sets demonstrate the effectiveness of our proposed paradigm.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62206303, 62001495)
- China Postdoctoral Science Foundation (48919)
- science and technology innovation Program of Hunan Province (2023RC3009)
This publication has 43 references indexed in Scilit:
- Similarity Modeling on Heterogeneous Networks via Automatic Path Discovery2019
- Modeling Relational Data with Graph Convolutional Networks2018
- Hybrid Recommendation in Heterogeneous NetworksLecture Notes in Computer Science, 2014
- Predicting drug–target interactions from chemical and genomic kernels using Bayesian matrix factorizationBioinformatics, 2012
- Relational retrieval using a combination of path-constrained random walksMachine Learning, 2010
- DBpedia: A Nucleus for a Web of Open Data2007
- The DBLP Computer Science Bibliography: Evolution, Research Issues, Perspectives2002
- The Protein Data BankNucleic Acids Research, 2000
- Sparse matrix multiplication package (SMMP)Advances in Computational Mathematics, 1993
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992