Research map / Learning theory and algorithms / Combinatorial and search optimization
A Constraint-Based Approach to Learning and Explanation
Gabriele Ciravegna, Francesco Giannini, Stefano Melacci, Marco Maggini, Marco Gori
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add learned-constraint mutual-information regularization (stage-based) | MLP task functions · MNIST Even/Odd, 1 label/class | accuracy (%): 31.7 -> 46.5 | Improved |
| add learned-constraint regularization (stage-based) | MLP task functions · MNIST Even/Odd, 100 labels/class | accuracy (%): 84.5 -> 86.7 | Improved |
| add learned-constraint regularization (stage-based) | ResNet50 features + MLP · PASCAL Multi, 10 labels/class | macro F1 (%): 54.0 -> 56.8 | Improved |
| add learned-constraint regularization (stage-based) | ResNet50 features + MLP · PASCAL Multi, whole dataset labeled | macro F1 (%): 62.6 -> 63.8 | Improved |
| use stage-based instead of global (joint) optimization (ablation) | IBLC · MNIST Even/Odd, 1 label/class | accuracy (%): 38.7 -> 46.5 | Improved |
| use stage-based instead of global (joint) optimization (ablation) | IBLC · MNIST Even/Odd, 10 labels/class | accuracy (%): 71.6 -> 71.5 | No clear effect |
| use stage-based instead of global (joint) optimization (ablation) | IBLC · PASCAL Multi, 10 labels/class | macro F1 (%): 55.8 -> 56.8 | Improved |
| use stage-based instead of global (joint) optimization (ablation) | IBLC · PASCAL Multi, whole dataset labeled | macro F1 (%): 63.7 -> 63.8 | No clear effect |
Closest papers by meaning
- Learning with Explanation Constraints (NeurIPS 2023 · similarity 0.87)
- DeepSaDe: Learning Neural Networks That Guarantee Domain Constraint Satisfaction (AAAI 2024 · similarity 0.84)
- Learning to Learn in Interactive Constraint Acquisition (AAAI 2024 · similarity 0.84)
- Constraints-Guided Diffusion Reasoner for Neuro-Symbolic Learning (AAAI 2026 · similarity 0.84)
- A learnability analysis on neuro-symbolic learning (NeurIPS 2025 · similarity 0.83)
- Generalizing Constraint Models in Constraint Acquisition (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
