AI Paper Atlas

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

Regularizing Black-box Models for Improved Interpretability

Gregory Plumb, Maruan Al-Shedivat, Ángel Alexander Cabrera, Adam Perer, Eric P. Xing, Ameet Talwalkar

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 38 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
add ExpO fidelity regularizer to trainingMLP regression models · UCI regression datasets (LIME/MAPLE)interpretability metrics (PF, NF, stability): e.g. winequality LIME-NF 0.0330 -> 0.0025Improved
add ExpO fidelity regularizerMLP regression models · communities, day, MSDtest MSE: communities 0.49 -> 0.46; MSD 0.583 -> 0.557Improved
use 1D-fidelity regularizer instead of full fidelity regularizer (ablation)ExpO · UCI regression datasetsinterpretability metrics: autompgs LIME-NF 0.011 -> 0.029 (None 0.041)Mixed
add ExpO fidelity regularizer to compare with SENN (tuned for accuracy)breast cancer classifier · breast canceraccuracy: 0.92 (SENN) -> 0.99Improved
add l1 or l2 regularization instead of ExpO (ablation)MLP regression models · UCI regression datasetsinterpretability metrics: housing LIME-NF 0.14 -> 0.13 (L1), 0.12 (L2)No clear effect
ExpO-regularized model vs normally trained model in human user studyexplanations for housing model · user studysteps to reach target: 11.45 -> 8.00Improved
add ExpO fidelity regularizer on support2 mortality classificationMLP classifier · SUPPORT2accuracyNo clear effect

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