让逻辑规则根据查询上下文动态调整权重，提升知识图谱补全的可解释性。
SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion
- 基于查询邻域子图动态计算规则重要性，实现上下文感知评分。
- 在多个基准数据集上表现优于传统规则方法，兼具高准确率与可解释性。
- 适合需要透明推理过程的场景，如医疗、金融等高可信领域。
基于逻辑规则的方法通过可读的推理规则捕捉复合关系，为知识图谱补全（KGC）提供可解释路径。现有方法通常对每条规则模式赋予全局权重，但在不同查询实例中规则重要性应有差异。为此，本文提出SLogic（子图感知逻辑规则学习）框架，为逻辑规则分配依赖查询的得分。其核心是上下文感知评分函数，通过分析查询头实体定义的局部子图，决定规则的重要性，从而实现针对特定查询上下文的差异化规则加权。该设计符合常识推理中的具体性原则。大量实验表明，SLogic在基准数据集上达到与先进规则方法相当的性能，并生成可读的、依赖查询的逻辑规则，作为推理过程的显式解释。
原文摘要 · Abstract (English)
Logical rule-based methods offer an interpretable approach to knowledge graph completion (KGC) by capturing compositional relationships in the form of human-readable inference rules. While existing logical rule-based methods learn rule confidence scores, they typically assign a global weight to each rule schema, applied uniformly across the graph. This is a significant limitation, as a rule's importance often varies depending on the specific query instance. To address this, we introduce SLogic (Subgraph-Informed Logical Rule learning), a novel framework that assigns query-dependent scores to logical rules. The core of SLogic is a context-aware scoring function. This framework is in line with the specificity principle in commonsense reasoning. This function determines the importance of a rule by analyzing the subgraph locally defined by the query's head entity, thereby enabling a differentiated weighting of rules specific to their local query contexts. Extensive experiments on benchmark datasets show that SLogic achieves competitive performance among rule-based methods. It also generates query-dependent, human-readable logical rules that serve as explicit explanations for its inferences.
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。