Differentiable Learning of Logical Rules for Knowledge Base Reasoning

2017/02/27 by Fan Yang, Zhilin Yang, Yang, Fan +3 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1702.08367

openalex publication_date 2017/02/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We study the problem of learning probabilistic first-order logical rules for knowledge base reasoning. This learning problem is difficult because it requires learning the parameters in a continuous space as well as the structure in a discrete space. We propose a framework, Neural Logic Programming, that combines the parameter and structure learning of first-order logical rules in an end-to-end differentiable model. This approach is inspired by a recently-developed differentiable logic called TensorLog, where inference tasks can be compiled into sequences of differentiable operations. We design a neural controller system that learns to compose these operations. Empirically, our method outperforms prior work on multiple knowledge base benchmark datasets, including Freebase and WikiMovies.

Citations

• TensorLog: A Differentiable Deductive Database
• Words or Characters? Fine-grained Gating for Reading Comprehension
• Modeling Relation Paths for Representation Learning of Knowledge Bases

Cited by

• Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
• Logical Rule Induction and Theory Learning Using Neural Theorem Proving
• AI Reasoning Systems: PAC and Applied Methods

Related

• Learning First-Order Rules with Differentiable Logic Program Semantics
• Differentiable Probabilistic Logic Networks
• End-to-End Differentiable Proving
• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks
• Logical Neural Networks