Towards Learning Instantiated Logical Rules from Knowledge Graphs

Abstract

Efficiently inducing high-level interpretable regularities from knowledge graphs (KGs) is an essential yet challenging task that benefits many downstream applications. In this work, we present GPFL, a probabilistic rule learner optimized to mine instantiated first-order logic rules from KGs. Instantiated rules contain constants extracted from KGs. Compared to abstract rules that contain no constants, instantiated rules are capable of explaining and expressing concepts in more details. GPFL utilizes a novel two-stage rule generation mechanism that first generalizes extracted paths into templates that are acyclic abstract rules until a certain degree of template saturation is achieved, then specializes the generated templates into instantiated rules. Unlike existing works that ground every mined instantiated rule for evaluation, GPFL shares groundings between structurally similar rules for collective evaluation. Moreover, we reveal the presence of overfitting rules, their impact on the predictive performance, and the effectiveness of a simple validation method filtering out overfitting rules. Through extensive experiments on public benchmark datasets, we show that GPFL 1.) significantly reduces the runtime on evaluating instantiated rules; 2.) discovers much more quality instantiated rules than existing works; 3.) improves the predictive performance of learned rules by removing overfitting rules via validation; 4.) is competitive on knowledge graph completion task compared to state-of-the-art baselines.

References in corpus (8)

• A Review of Relational Machine Learning for Knowledge Graphs
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Quaternion Knowledge Graph Embeddings
• Variational Reasoning for Question Answering with Knowledge Graph
• Differentiable Learning of Logical Rules for Knowledge Base Reasoning
• "I Wanted to Predict Elections with Twitter and all I got was this Lousy Paper" -- A Balanced Survey on Election Prediction using Twitter Data
• Improving the Efficiency of Inductive Logic Programming Through the Use of Query Packs
• DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs

Cited by in corpus (3)

• Rule Mining over Knowledge Graphs via Reinforcement Learning
• SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models
• Building Rule Hierarchies for Efficient Logical Rule Learning from Knowledge Graphs