Neuro-Logic Lifelong Learning

TL;DR

This paper proposes a lifelong learning framework for ILP using neural networks, emphasizing the reuse of logic rules across tasks to improve scalability and performance in Neural-Symbolic AI.

Contribution

It introduces a compositional framework for lifelong learning in ILP, enabling transfer of logic rules between tasks, which is a novel approach in Neural-Symbolic AI.

Findings

Logic rules can be effectively reused across tasks.

The framework improves learning efficiency and scalability.

Empirical results show successful transfer and performance gains.

Abstract

Solving Inductive Logic Programming (ILP) problems with neural networks is a key challenge in Neural-Symbolic Ar- tificial Intelligence (AI). While most research has focused on designing novel network architectures for individual prob- lems, less effort has been devoted to exploring new learning paradigms involving a sequence of problems. In this work, we investigate lifelong learning ILP, which leverages the com- positional and transferable nature of logic rules for efficient learning of new problems. We introduce a compositional framework, demonstrating how logic rules acquired from ear- lier tasks can be efficiently reused in subsequent ones, leading to improved scalability and performance. We formalize our approach and empirically evaluate it on sequences of tasks. Experimental results validate the feasibility and advantages of this paradigm, opening new directions for continual learn- ing in Neural-Symbolic AI.