DeepStochLog: Neural Stochastic Logic Programming (Extended Abstract)

Authors: Thomas Winters, Giuseppe Marra, Robin Manhaeve, Luc De Raedt
Publication Date: 2021-10
Publication Venue: 15th International Workshop on Neural-Symbolic Learning and Reasoning
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.

Citation

APA

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

Harvard

Winters, T. et al. (2022) “DeepStochLog: Neural Stochastic Logic Programming,” Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), pp. 10090–10100. doi:10.1609/aaai.v36i9.21248.

Vancouver

Winters T, Marra G, Manhaeve R, Raedt LD. DeepStochLog: Neural Stochastic Logic Programming. Proceedings of the AAAI Conference on Artificial Intelligence [Internet]. 2022;36(9):10090–100. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/21248

BibTeX

@article{Winters_Marra_Manhaeve_Raedt_2022,
	title        = {DeepStochLog: Neural Stochastic Logic Programming},
	author       = {Winters, Thomas and Marra, Giuseppe and Manhaeve, Robin and Raedt, Luc De},
	year         = 2022,
	month        = {Jun.},
	journal      = {Proceedings of the AAAI Conference on Artificial Intelligence},
	volume       = 36,
	number       = 9,
	pages        = {10090--10100},
	doi          = {10.1609/aaai.v36i9.21248},
	url          = {https://ojs.aaai.org/index.php/AAAI/article/view/21248},
	abstractnote = {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.}
}

Related project

2021

contributor

DeepStochLog

Neural Stochastic Logic Programming

Back to all publications