DeepProbLog: Neural Probabilistic Logic Programming

Abstract

We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques can be adapted for the new language. Our experiments demonstrate that DeepProbLog supports both symbolic and subsymbolic representations and inference, 1) program induction, 2) probabilistic (logic) programming, and 3) (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.

Accepted for spotlight at NeurIPS 2018

References in corpus (3)

• A simple neural network module for relational reasoning
• End-to-End Differentiable Proving
• Tunneling Neural Perception and Logic Reasoning through Abductive Learning

Cited by in corpus (13)

• Neural Collaborative Reasoning
• LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
• Discrete and continuous representations and processing in deep learning: Looking forward
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Logical Rule Induction and Theory Learning Using Neural Theorem Proving
• Analyzing Differentiable Fuzzy Logic Operators
• SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming
• Using DeepProbLog to perform Complex Event Processing on an Audio Stream
• pix2rule: End-to-end Neuro-symbolic Rule Learning
• MatSat: a matrix-based differentiable SAT solver
• Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms
• RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools
• Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning