RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs

Abstract

This paper studies learning logic rules for reasoning on knowledge graphs. Logic rules provide interpretable explanations when used for prediction as well as being able to generalize to other tasks, and hence are critical to learn. Existing methods either suffer from the problem of searching in a large search space (e.g., neural logic programming) or ineffective optimization due to sparse rewards (e.g., techniques based on reinforcement learning). To address these limitations, this paper proposes a probabilistic model called RNNLogic. RNNLogic treats logic rules as a latent variable, and simultaneously trains a rule generator as well as a reasoning predictor with logic rules. We develop an EM-based algorithm for optimization. In each iteration, the reasoning predictor is first updated to explore some generated logic rules for reasoning. Then in the E-step, we select a set of high-quality rules from all generated rules with both the rule generator and reasoning predictor via posterior inference; and in the M-step, the rule generator is updated with the rules selected in the E-step. Experiments on four datasets prove the effectiveness of RNNLogic.

iclr 2021

References in corpus (7)

• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
• Stochastic Logic Programs: Sampling, Inference and Applications
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• Learning Reasoning Strategies in End-to-End Differentiable Proving

Cited by in corpus (7)

• Knowledge Graph Reasoning with Relational Digraph
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• EvoPath: Evolutionary Meta-path Discovery with Large Language Models for Complex Heterogeneous Information Networks
• Learning Symbolic Rules for Reasoning in Quasi-Natural Language
• Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
• Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion
• Learning Logic Rules for Document-level Relation Extraction