DeepStochLog: Neural Stochastic Logic Programming

Authors

  • Thomas Winters KU Leuven
  • Giuseppe Marra KU Leuven
  • Robin Manhaeve KU Leuven
  • Luc De Raedt KU Leuven Örebro University

DOI:

https://doi.org/10.1609/aaai.v36i9.21248

Keywords:

Reasoning Under Uncertainty (RU), Machine Learning (ML)

Abstract

Recent advances in neural-symbolic learning, such as DeepProbLog, extend probabilistic logic programs with neural predicates. Like graphical models, these probabilistic logic programs define a probability distribution over possible worlds, for which inference is computationally hard. We propose DeepStochLog, an alternative neural-symbolic framework based on stochastic definite clause grammars, a kind of stochastic logic program. More specifically, we introduce neural grammar rules into stochastic definite clause grammars to create a framework that can be trained end-to-end. We show that inference and learning in neural stochastic logic programming scale much better than for neural probabilistic logic programs. Furthermore, the experimental evaluation shows that DeepStochLog achieves state-of-the-art results on challenging neural-symbolic learning tasks.

Downloads

Published

2022-06-28

How to Cite

Winters, T., Marra, G., Manhaeve, R., & Raedt, L. D. (2022). DeepStochLog: Neural Stochastic Logic Programming. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 10090-10100. https://doi.org/10.1609/aaai.v36i9.21248

Issue

Section

AAAI Technical Track on Reasoning under Uncertainty