Neural Logic Machines

Abstract

We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic processor for objects with properties, relations, logic connectives, and quantifiers. After being trained on small-scale tasks (such as sorting short arrays), NLMs can recover lifted rules, and generalize to large-scale tasks (such as sorting longer arrays). In our experiments, NLMs achieve perfect generalization in a number of tasks, from relational reasoning tasks on the family tree and general graphs, to decision making tasks including sorting arrays, finding shortest paths, and playing the blocks world. Most of these tasks are hard to accomplish for neural networks or inductive logic programming alone.

ICLR 2019. Project page: https://sites.google.com/view/neural-logic-machines

Cited by in corpus (22)

• Neural Collaborative Reasoning
• From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
• Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
• Learn to Explain Efficiently via Neural Logic Inductive Learning
• Differentiable Logic Machines
• Learning Symbolic Rules for Reasoning in Quasi-Natural Language
• Compositional Generalization via Neural-Symbolic Stack Machines
• Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Neural Logic Reasoning
• Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces
• Neural Status Registers
• NeuralLog: a Neural Logic Language
• Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
• EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
• Consistency-Aware Graph Network for Human Interaction Understanding
• Neuro-Symbolic Reinforcement Learning with First-Order Logic
• Program Enhanced Fact Verification with Verbalization and Graph Attention Network
• RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools
• Exploring End-to-End Differentiable Natural Logic Modeling
• Neural Unification for Logic Reasoning over Natural Language
• Logic and the $2$-Simplicial Transformer