DeepStochLog: Neural Stochastic Logic Programming

TL;DR

DeepStochLog introduces a neural stochastic logic programming framework based on stochastic definite clause grammars, enabling efficient inference and training, and achieving state-of-the-art results in neural symbolic learning tasks.

Contribution

It presents a novel neural stochastic logic programming framework that improves scalability and performance over existing neural probabilistic logic programs.

Findings

Scales better than neural probabilistic logic programs

Achieves state-of-the-art results on neural symbolic learning tasks

Enables end-to-end training of neural grammar rules

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 type of stochastic logic program, which defines a probability distribution over possible derivations. 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.