knowledge-graph-reasoning

This paper introduces GRiD, a framework that uses diffusion models and reinforcement learning to generate graph-like rules (e.g., cycles, branches) for knowledge graph reasoning, addressing the limitations of existing chain-rule mining methods. Experiments on six benchmarks show competitive performance in KG completion tasks.

This paper proposes a strikingness-aware evaluation framework for Temporal Knowledge Graph Reasoning (TKGR) that weights events by rarity to better assess model reasoning, addressing overestimation from trivial repeated events.