Neural models speed up constraint learning with less user input
Learning Symbolic Constraint Representations from Examples: A Neuro-Symbolic Approach
Artificial Intelligence
Summary
Learning complex rules from examples usually needs lots of questions answered by a human, which takes a lot of time. The authors created a system that uses neural networks to mimic human answers, so it asks fewer questions and learns faster. This system then works with a special solver to turn those answers into clear rules computers can understand. Their approach helps combine quick pattern spotting with precise logical thinking to build models automatically, even when no prior knowledge is given.
What this means in practice
- •For software developers: Automatically build rule-based models from example data with minimal user input in complex software systems.
- •For industrial automation teams: Create interpretable constraint models from operational examples to improve automation without expert involvement.
Authors
Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker
Abstract
Learning user-defined concepts as constraint networks has been extensively studied in the constraint acquisition (CA) literature. However, existing approaches typically rely on intensive interactions with a human oracle, making the learning process costly in terms of time and number of queries. In this paper, we propose a neuro-symbolic framework for automatic CA that significantly reduces user involvement by introducing neural Oracle Transformer models which learn to emulate user responses and to generalize conceptual knowledge. Trained on previously available examples, the learned oracle interacts with a dedicated CA engine, FastCA, which systematically refines the oracle's responses into a sound, consistent, and interpretable constraint network. This neuro-symbolic interaction enables the recovery of structured symbolic models from data without prior domain knowledge. Our results demonstrate that this neuro-symbolic interplay effectively aligns data-driven pattern recognition with symbolic reasoning, offering a robust approach to automating model construction in combinatorial domains.