DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs

Abstract

In this paper, we study the problem of learning probabilistic logical rules for inductive and interpretable link prediction. Despite the importance of inductive link prediction, most previous works focused on transductive link prediction and cannot manage previously unseen entities. Moreover, they are black-box models that are not easily explainable for humans. We propose DRUM, a scalable and differentiable approach for mining first-order logical rules from knowledge graphs which resolves these problems. We motivate our method by making a connection between learning confidence scores for each rule and low-rank tensor approximation. DRUM uses bidirectional RNNs to share useful information across the tasks of learning rules for different relations. We also empirically demonstrate the efficiency of DRUM over existing rule mining methods for inductive link prediction on a variety of benchmark datasets.

Cited by in corpus (15)

• Knowledge Graphs
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
• Inductive Relation Prediction by Subgraph Reasoning
• Evaluating Logical Generalization in Graph Neural Networks
• Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
• Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction
• Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
• Towards Learning Instantiated Logical Rules from Knowledge Graphs
• Role-Aware Modeling for N-ary Relational Knowledge Bases
• Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
• Relational Message Passing for Knowledge Graph Completion
• Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification
• Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
• Convex Polytope Trees