Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models
Quick Take
The GRiD framework introduces a novel approach to knowledge graph reasoning by generating graph-like rules through a two-phase training strategy, achieving competitive performance on KG completion tasks across six benchmark datasets. It combines supervised pre-training with reinforcement learning to optimize rule quality metrics, addressing limitations of traditional rule mining methods focused on simpler structures.
Key Points
- GRiD reformulates graph-like rule discovery as a discrete generative process.
- The framework employs supervised pre-training and reinforcement learning for optimization.
- Experiments show GRiD's competitive performance on knowledge graph completion tasks.
- Ablation studies confirm GRiD's efficiency and robustness in rule generation.
- Graph-like rules generated by GRiD complement traditional chain-like rules.
Article Content
From source RSS / original summaryarXiv:2605. 30747v1 Announce Type: new Abstract: Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. However, existing rule mining methods predominantly focus on simple chain-like rules and therefore neglect the richer relational information encoded in graph-like structures, such as cycles and branches.
This limitation is further exacerbated by computational bottlenecks caused by the combinatorial explosion of the search space, which is especially challenging for graph-like rules. Meanwhile, generative approaches such as diffusion models, despite their success in other domains, can not be directly applied to rule mining because their training objectives are not aligned with the goal of learning high-quality rules, and non-differentiable KG rule quality metrics cannot directly guide model optimization.
To address these limitations, we propose GRiD, a framework that reformulates graph-like rule discovery as a discrete generative process conditioned on the target relation. GRiD employs a two-phase training strategy. First, supervised pre-training enables GRiD to capture structural priors from subgraphs sampled from the KG meta-graph. Subsequently, reinforcement learning is applied to fine-tune GRiD through policy gradient optimization guided directly by non-differentiable rule-quality metrics.
Experiments on six benchmark datasets show that GRiD achieves competitive performance on KG completion tasks. Ablation studies confirm the efficiency and robustness of GRiD and further show that graph-like rules complement chain-like rules in KG completion. Our codes and datasets are available in https://github. com/Haoxiang-Cheng/GRiD
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane
The Redpanda Agentic Data Plane (ADP) introduces out-of-band metadata channels to enhance the safety of autonomous AI agents, ensuring secure data access and tamper-proof audit trails. This architecture mitigates risks associated with unpredictable AI behavior by enforcing governance throughout the agent lifecycle, demonstrated in a multi-agent trading system with strict data scoping and approval thresholds.