Neural probabilistic logic programming in DeepProbLog

• Published in: Artificial intelligence Vol. 298; p. 103504
• Main Authors: Manhaeve, Robin, Dumančić, Sebastijan, Kimmig, Angelika, Demeester, Thomas, De Raedt, Luc
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.09.2021; Elsevier Science Ltd
• Subjects: Computer Science; Datavetenskap; Deep learning; Inference; Learning and reasoning; Logic; Logic programming; Neural networks; Neuro-symbolic integration; Probabilistic logic programming; Probability; Programming languages; Probability; Logic; Learning and reasoning; Neural networks; Probabilistic logic programming; Neuro-symbolic integration
• ISSN: 0004-3702; 1872-7921; 1872-7921
• DOI: 10.1016/j.artint.2021.103504

We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that DeepProbLog supports (i) both symbolic and subsymbolic representations and inference, (ii) program induction, (iii) probabilistic (logic) programming, and (iv) (deep) learning from examples. To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that exploits the full expressiveness and strengths of both worlds and can be trained end-to-end based on examples.