AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Towards Robust Interpretability with Self-Explaining Neural Networks

David Alvarez Melis, Tommi Jaakkola

NeurIPS 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 414 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use SENN instead of logistic classificationCOMPAS · COMPAS test setaccuracy: 78.54% -> 82.02%Improved
Add gradient regularization (λ=1) rather than use the unregularized model (λ=0) (ablation)SENN · MNIST test setaccuracy: 99.11% -> 98.7%Hurt
Add gradient regularization (ablation)SENN · COMPAS and Breast-Cancerexplanation stabilityImproved
Add gradient regularization (ablation)SENN · COMPAS and Breast-Cancerprediction accuracyMixed
Use SENN rather than SHAP for explanation generationCOMPAS · COMPASexplanation robustness L: 6.78 -> 0.57Improved
Use SENN rather than LIME for explanation generationCOMPAS · COMPASexplanation robustness L: 8.36 -> 0.57Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy