SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion

2025/09/30 by Trung Le, Le, Trung Hoang, Tran Cao Son +3
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Rough Sets and Fuzzy Logic

paper · pdf · doi:10.48550/arxiv.2510.00279

openalex publication_date 2025/09/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 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 outperforms existing rule-based methods and achieves competitive performance against state-of-the-art baselines. It also generates query-dependent, human-readable logical rules that serve as explicit explanations for its inferences.

Citations

• Neural Compositional Rule Learning for Knowledge Graph Reasoning
• A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
• Rule-Guided Compositional Representation Learning on Knowledge Graphs
• Inductive Relation Prediction by Subgraph Reasoning
• DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
• Probabilistic Logic Neural Networks for Reasoning
• Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
• Fast Graph Representation Learning with PyTorch Geometric
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex\n Space
• Link Prediction Based on Graph Neural Networks
• TensorLog: Deep Learning Meets Probabilistic DBs
• Convolutional 2D Knowledge Graph Embeddings
• Modeling Relational Data with Graph Convolutional Networks
• Complex Embeddings for Simple Link Prediction
• Embedding Entities and Relations for Learning and Inference in Knowledge Bases
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Distributed Representations of Words and Phrases and their Compositionality
• Probable Inference, the Law of Succession, and Statistical Inference

Related

• Rule Learning over Knowledge Graphs: A Review
• RulE: Knowledge Graph Reasoning with Rule Embedding
• Neural Compositional Rule Learning for Knowledge Graph Reasoning
• Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
• DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning