Differentiable Logic Programming for Distant Supervision

TL;DR

This paper presents a differentiable approach to integrating neural networks with logic programming for distant supervision, enabling efficient learning without symbolic solvers and improving accuracy and speed.

Contribution

It introduces a novel differentiable logic programming method that embeds neural outputs and logic constraints into matrices, bypassing the need for symbolic solvers in NeSy learning.

Findings

Matches or exceeds existing methods in accuracy

Speeds up the learning process

Effective under limited labeled data

Abstract

We introduce a new method for integrating neural networks with logic programming in Neural-Symbolic AI (NeSy), aimed at learning with distant supervision, in which direct labels are unavailable. Unlike prior methods, our approach does not depend on symbolic solvers for reasoning about missing labels. Instead, it evaluates logical implications and constraints in a differentiable manner by embedding both neural network outputs and logic programs into matrices. This method facilitates more efficient learning under distant supervision. We evaluated our approach against existing methods while maintaining a constant volume of training data. The findings indicate that our method not only matches or exceeds the accuracy of other methods across various tasks but also speeds up the learning process. These results highlight the potential of our approach to enhance both accuracy and learning efficiency in NeSy applications.