AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

Martin Pawelczyk, Sascha Bielawski, Johan Van den Heuvel, Tobias Richter, Gjergji Kasneci

NeurIPS 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Counterfactual explanations and recourse · 11 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 AR, AR-LIME, or DICE rather than other independence-based methodsIndependence-based recourse methods · Adult, GMC, COMPASredundancyImproved
Use CEM rather than other independence-based methodsIndependence-based recourse methods · Adult, GMC, COMPAScost (l1)Improved
Use GS rather than other independence-based methodsIndependence-based recourse methods · Adult, GMC, COMPAStimeImproved
Use dependence-based rather than independence-based recourse methodsCounterfactual recourse methods · Adult, GMC, COMPASyNNImproved
Use FACE-EPS rather than other dependence-based methodsDependence-based recourse methods · Adult, GMC, COMPASyNNImproved
Use CLUE or REVISE rather than FACE for l1 recourse costDependence-based recourse methods · Adult, GMC, COMPAScost (l1)Improved
Use CLUE or REVISE rather than FACEDependence-based recourse methods · Adult, GMC, COMPAScost (l0)Hurt
Use generative methods CEM-VAE, CLUE, or REVISEDependence-based recourse methods · Adult, GMC, COMPAStimeImproved
Tune CLUE hyperparameters rather than use the defaults (ablation)CLUE · Recourse cost at fixed success ratedistanceNo clear effect
Use smaller GS sphere-growth steps (ablation)GS · Counterfactual generationtimeHurt
Use larger GS sphere-growth steps (ablation)GS · Counterfactual generationperformanceHurt
Set GS sphere-growth step size to 0.02 (ablation)GS · Counterfactual generationperformanceImproved

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