用双曲空间提升知识图谱逻辑查询的推理能力
Neural-Symbolic Logic Query Answering in Non-Euclidean Space
- 将逻辑查询分解为关系投影与模糊集运算，增强可解释性
- 在双曲空间中用GNN补全缺失链接，提升查询准确率
- 适合需要结构化推理与高透明度的智能问答场景
在知识图谱上回答复杂一阶逻辑（FOL）查询对推理至关重要。符号方法具可解释性但难以处理不完整图谱，神经方法泛化性强但缺乏透明度。神经符号模型虽试图融合两者优势，却常无法捕捉逻辑查询的层次结构，限制了性能。本文提出HYQNET，一种基于双曲空间的神经符号模型，用于逻辑查询推理。该模型将FOL查询分解为关系投影与模糊集上的逻辑运算，提升可解释性。为应对缺失链接，采用基于双曲GNN的知识图谱补全方法，在双曲空间中有效嵌入递归查询树并保留结构依赖。利用双曲表示，HYQNET比欧氏方法更有效地捕捉逻辑投影推理的层次特性。在三个基准数据集上的实验表明，HYQNET表现优异，凸显双曲空间推理的优势。
原文摘要 · Abstract (English)
Answering complex first-order logic (FOL) queries on knowledge graphs is essential for reasoning. Symbolic methods offer interpretability but struggle with incomplete graphs, while neural approaches generalize better but lack transparency. Neural-symbolic models aim to integrate both strengths but often fail to capture the hierarchical structure of logical queries, limiting their effectiveness. We propose HYQNET, a neural-symbolic model for logic query reasoning that fully leverages hyperbolic space. HYQNET decomposes FOL queries into relation projections and logical operations over fuzzy sets, enhancing interpretability. To address missing links, it employs a hyperbolic GNN-based approach for knowledge graph completion in hyperbolic space, effectively embedding the recursive query tree while preserving structural dependencies. By utilizing hyperbolic representations, HYQNET captures the hierarchical nature of logical projection reasoning more effectively than Euclidean-based approaches. Experiments on three benchmark datasets demonstrate that HYQNET achieves strong performance, highlighting the advantages of reasoning in hyperbolic space.
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。