Research map / Label-efficient and robust learning / Recognition and long-tail
Entropy-Based Logic Explanations of Neural Networks
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Pietro Lió, Marco Gori, Stefano Melacci
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 |
|---|---|---|---|
| Use entropy-based concept selection and logic explanations instead of a decision tree | MIMIC-II classification · MIMIC-II | accuracy (%): 77.53 ± 1.45 -> 79.05 ± 1.35 | Improved |
| Use entropy-based concept selection and logic explanations instead of BRL | V-Dem classification · V-Dem | accuracy (%): 91.23 ± 0.75 -> 94.51 ± 0.48 | Improved |
| Use entropy-based concept selection and logic explanations instead of a standard neural network | V-Dem classification · V-Dem | accuracy (%): 94.53 ± 1.17 -> 94.51 ± 0.48 | No clear effect |
| Use entropy-based concept selection and logic explanations instead of a random forest | MNIST even/odd classification · MNIST | accuracy (%): 99.96 ± 0.01 -> 99.81 ± 0.02 | Hurt |
| Use entropy-based concept selection and logic explanations instead of BRL | CUB classification · CUB | accuracy (%): 90.79 ± 0.34 -> 92.95 ± 0.20 | Improved |
| Use entropy-based explanations instead of ψ net explanations | Explanation fidelity on all four datasets · MIMIC-II, V-Dem, MNIST, CUB | fidelity (%): MIMIC-II: 51.63 ± 6.67 -> 79.11 ± 2.02; V-Dem: 69.67 ± 10.43 -> 90.90 ± 1.23; MNIST: 65.68 ± 5.05 -> 99.63 ± 0.00; CUB: | Improved |
| Replace L1 regularization with entropy regularization while keeping the Entropy Layer (ablation) | Toy Boolean classification tasks · Toy dataset | concept relevance identification | Improved |
| Add the Entropy Layer as the first layer instead of using a standard linear first layer (ablation) | Toy Boolean classification tasks · Toy dataset | concept relevance interpretability | Improved |
| Vary τ and λ across the reported V-Dem grid (ablation) | Entropy net · V-Dem | model accuracy (%): 94.05 ± 0.58 to 94.86 ± 0.23 | No clear effect |
Closest papers by meaning
- Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations (ICML 2025 · similarity 0.86)
- Neural Reasoning Networks: Efficient Interpretable Neural Networks with Automatic Textual Explanations (AAAI 2025 · similarity 0.85)
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.85)
- Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable? (ICLR 2025 · similarity 0.84)
- Factor Graph-based Interpretable Neural Networks (ICLR 2025 · similarity 0.84)
- Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective (ICML 2025 · similarity 0.84)
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.
