Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Robust Interpretability with Self-Explaining Neural Networks
David Alvarez Melis, Tommi Jaakkola
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 |
|---|---|---|---|
| Use SENN instead of logistic classification | COMPAS · COMPAS test set | accuracy: 78.54% -> 82.02% | Improved |
| Add gradient regularization (λ=1) rather than use the unregularized model (λ=0) (ablation) | SENN · MNIST test set | accuracy: 99.11% -> 98.7% | Hurt |
| Add gradient regularization (ablation) | SENN · COMPAS and Breast-Cancer | explanation stability | Improved |
| Add gradient regularization (ablation) | SENN · COMPAS and Breast-Cancer | prediction accuracy | Mixed |
| Use SENN rather than SHAP for explanation generation | COMPAS · COMPAS | explanation robustness L: 6.78 -> 0.57 | Improved |
| Use SENN rather than LIME for explanation generation | COMPAS · COMPAS | explanation robustness L: 8.36 -> 0.57 | Improved |
Closest papers by meaning
- Explainable Neural Networks with Guarantee: A Sparse Estimation Approach (AAAI 2025 · similarity 0.89)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.89)
- Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable? (ICLR 2025 · similarity 0.88)
- Enhancing Performance of Explainable AI Models with Constrained Concept Refinement (ICML 2025 · similarity 0.88)
- Redundancy Undermines the Trustworthiness of Self-Interpretable GNNs (ICML 2025 · similarity 0.88)
- Towards Modeling Uncertainties of Self-Explaining Neural Networks via Conformal Prediction (AAAI 2024 · similarity 0.87)
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.
