Differentiable Logic Programming for Distant Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Takemura, Akihiro, Inoue, Katsumi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910575625240576
author Takemura, Akihiro
Inoue, Katsumi
author_facet Takemura, Akihiro
Inoue, Katsumi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12591
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Differentiable Logic Programming for Distant Supervision
Takemura, Akihiro
Inoue, Katsumi
Artificial Intelligence
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.
title Differentiable Logic Programming for Distant Supervision
topic Artificial Intelligence
url https://arxiv.org/abs/2408.12591