Variable Assignment Invariant Neural Networks for Learning Logic Programs

TL;DR

This paper introduces a variable assignment invariant neural network technique for learning logic programs that is robust to variable permutations, improving scalability and effectiveness in noisy symbolic domains.

Contribution

It presents a novel neural network approach leveraging variable permutation invariance to enhance learning of logic programs from state transitions.

Findings

Effective in noisy environments

Scalable to complex domains

Code publicly available

Abstract

Learning from interpretation transition (LFIT) is a framework for learning rules from observed state transitions. LFIT has been implemented in purely symbolic algorithms, but they are unable to deal with noise or generalize to unobserved transitions. Rule extraction based neural network methods suffer from overfitting, while more general implementation that categorize rules suffer from combinatorial explosion. In this paper, we introduce a technique to leverage variable permutation invariance inherent in symbolic domains. Our technique ensures that the permutation and the naming of the variables would not affect the results. We demonstrate the effectiveness and the scalability of this method with various experiments. Our code is publicly available at https://github.com/phuayj/delta-lfit-2