Paper Overview
Research Area: Machine Learning Authors: Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar, Helge Spieker Published: 2026-09-15 arXiv: 2609.12267
Summary
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. This paper proposes 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. The results show that this neuro-symbolic collaboration effectively aligns data-driven pattern recognition with symbolic reasoning, providing a robust path toward automated model construction for combinatorial optimization.
Key Contributions
- A neuro-symbolic framework for automatic constraint acquisition that minimizes human oracle involvement
- Neural Oracle Transformer models trained on existing examples to emulate user responses and generalize conceptual knowledge
- FastCA, a dedicated CA engine that refines oracle answers into sound, consistent, interpretable constraint networks
*Auto-collected on 2026-09-15*