Inductive Meta-Path Learning for Schema-Complex Heterogeneous Information Networks

• Published in: IEEE transactions on pattern analysis and machine intelligence 2024-12, Vol.46 (12), p.10196-10209
• Main Authors: Liu, Shixuan, Fan, Changjun, Cheng, Kewei, Wang, Yunfei, Cui, Peng, Sun, Yizhou, Liu, Zhong
• Format: Article
• Language: English
• Subjects: Cognition; Fans; Heterogeneous information networks; inductive meta-path learning; meta-paths discovery; Semantics; Sun; Task analysis; Training; Urban areas
• ISSN: 0162-8828; 1939-3539; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2024.3435055

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.