通过关系依赖图实现高效知识图谱推理，支持全新实体与关系的预测。
GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs
- 构建关系依赖图，用有向链接捕捉关系间的组合规律。
- 在60个基准上，全归纳场景下性能提升最高达25%。
- 适合需要泛化到新关系和实体的研究者使用。
在完全归纳设置下，测试时的实体和关系均未在训练中出现，知识图谱推理仍是开放挑战。本文提出GraphOracle框架，将每个知识图谱转换为关系依赖图（RDG），编码关系间的有向先后关系，捕捉关键组合模式的同时显著降低图密度。基于查询关系，多头注意力机制在RDG上传播信息，生成上下文感知的关系嵌入。这些嵌入引导第二个图神经网络在原始知识图谱上进行归纳消息传递，实现对全新实体和关系的预测。在60个基准上的综合实验表明，GraphOracle在全归纳场景下性能优于先前方法最多25%，在跨域场景下提升达28%。分析进一步确认，紧凑的RDG结构与基于注意力的传播是实现高效准确泛化的关键。
原文摘要 · Abstract (English)
Knowledge graph reasoning in the fully-inductive setting, where both entities and relations at test time are unseen during training, remains an open challenge. In this work, we introduce GraphOracle, a novel framework that achieves robust fully-inductive reasoning by transforming each knowledge graph into a Relation-Dependency Graph (RDG). The RDG encodes directed precedence links between relations, capturing essential compositional patterns while drastically reducing graph density. Conditioned on a query relation, a multi-head attention mechanism propagates information over the RDG to produce context-aware relation embeddings. These embeddings then guide a second GNN to perform inductive message passing over the original knowledge graph, enabling prediction on entirely new entities and relations. Comprehensive experiments on 60 benchmarks demonstrate that GraphOracle outperforms prior methods by up to 25% in fully-inductive and 28% in cross-domain scenarios. Our analysis further confirms that the compact RDG structure and attention-based propagation are key to efficient and accurate generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。