EvoPath: Evolutionary Meta-path Discovery with Large Language Models for Complex Heterogeneous Information Networks

Abstract

Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although their utility is constrained by discovery challenges. While Large Language Models (LLMs) offer new prospects for meta-path discovery due to their extensive knowledge encoding and efficiency, their adaptation faces challenges such as corpora bias, lexical discrepancies, and hallucination. This paper pioneers the mitigation of these challenges by presenting EvoPath, an innovative framework that leverages LLMs to efficiently identify high-quality meta-paths. EvoPath is carefully designed, with each component aimed at addressing issues that could lead to potential knowledge conflicts. With a minimal subset of HIN facts, EvoPath iteratively generates and evolves meta-paths by dynamically replaying meta-paths in the buffer with prioritization based on their scores. Comprehensive experiments on three large, complex HINs with hundreds of relations demonstrate that our framework, EvoPath, enables LLMs to generate high-quality meta-paths through effective prompting, confirming its superior performance in HIN reasoning tasks. Further ablation studies validate the effectiveness of each module within the framework.

References in corpus (15)

• LLaMA: Open and Efficient Foundation Language Models
• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Efficiently Summarising Event Sequences with Rich Interleaving Patterns
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• GLM-130B: An Open Bilingual Pre-trained Model
• RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
• Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
• Genetic Meta-Structure Search for Recommendation on Heterogeneous Information Network
• Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks
• Neural Compositional Rule Learning for Knowledge Graph Reasoning
• ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning
• Adaptive Intellect Unleashed: The Feasibility of Knowledge Transfer in Large Language Models
• Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning