Deep Learning with Logical Constraints

Abstract

In recent years, there has been an increasing interest in exploiting logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e.g., for safety-critical applications. In this survey, we retrace such works and categorize them based on (i) the logical language that they use to express the background knowledge and (ii) the goals that they achieve.

Survey paper. IJCAI 2022

References in corpus (6)

• Distilling the Knowledge in a Neural Network
• DeepGO: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier
• A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks
• Incorporating Domain Knowledge into Deep Neural Networks
• Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
• Neuro-Symbolic Constraint Programming for Structured Prediction

Cited by in corpus (4)

• ROAD-R: The Autonomous Driving Dataset with Logical Requirements
• Comparing differentiable logics for learning with logical constraints
• Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report
• Integrating Background Knowledge in Medical Semantic Segmentation with Logic Tensor Networks