AINeutralarXiv – CS AI · 5h ago6/10
🧠
Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models
Researchers introduce GRiD, a novel framework using diffusion models and reinforcement learning to discover complex graph-like rules for knowledge graph reasoning, moving beyond traditional chain-based rule mining. The approach combines supervised pre-training with policy gradient optimization to generate interpretable logical rules while overcoming computational bottlenecks, achieving competitive performance on KG completion benchmarks.