Neuro-Symbolic Hierarchical Rule Induction

2021/12/26 by Claire Glanois, Xuening Feng, Glanois, Claire +9 · 5 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #I.2.3 #I.2.6 #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #Topic Modeling

paper · doi:10.48550/arxiv.2112.13418

openalex publication_date 2021/12/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems. In this model, which is built from a set of meta-rules organised in a hierarchical structure, first-order rules are invented by learning embeddings to match facts and body predicates of a meta-rule. To instantiate it, we specifically design an expressive set of generic meta-rules, and demonstrate they generate a consequent fragment of Horn clauses. During training, we inject a controlled \pwGumbel noise to avoid local optima and employ interpretability-regularization term to further guide the convergence to interpretable rules. We empirically validate our model on various tasks (ILP, visual genome, reinforcement learning) against several state-of-the-art methods.

Citations

• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Learning Algorithms via Neural Logic Networks

Cited by

• Neuro-Logic Lifelong Learning
• RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models
• LLM-Generated Explanations Do Not Suffice for Ultra-Strong Machine Learning
• Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies
• Disentangling Neural Disjunctive Normal Form Models

Related

• Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks
• Learning First-Order Rules with Differentiable Logic Program Semantics
• Learn to Explain Efficiently via Neural Logic Inductive Learning
• Logical Rule Induction and Theory Learning Using Neural Theorem Proving
• Neurosymbolic Methods for Rule Mining