Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks

TL;DR

This paper introduces SchemaWalk, an inductive framework for learning meaningful meta-paths in complex heterogeneous information networks, overcoming enumeration challenges through schema-level representations and reinforcement learning.

Contribution

The paper presents a novel inductive meta-path learning method that efficiently handles schema-complex HINs using schema-level representations and a reinforcement learning agent.

Findings

SchemaWalk effectively learns high-quality meta-paths in complex HINs.

The framework reduces computational complexity compared to enumeration-based methods.

Experimental results show improved performance on real-world datasets.

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.