AI Paper Atlas

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

Joint Distribution–Informed Shapley Values for Sparse Counterfactual Explanations

Lei You, Yijun Bian, Lele Cao

ICLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations · 2 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 counterfactual-informed Shapley with OT coupling instead of uniform coupling (ablation)p-SHAP (COLA) · Hotel Bookings, 80% effectnumber of modified features: 7.01 -> 2.50Improved
use OT coupling instead of random coupling (ablation)p-SHAP (COLA) · Hotel Bookings, 80% effectnumber of modified features: 10.63 -> 2.50Improved
use OT coupling instead of random coupling (ablation)p-SHAP (COLA) · COMPAS, 80% effectnumber of modified features: 2.58 -> 1.25Improved
use counterfactual information in the Shapley background instead of the random training-set baseline (with OT coupling) (ablation)p-SHAP (COLA) · Hotel Bookings, 80% effectnumber of modified features: 8.55 -> 2.50Improved
use counterfactual information in the Shapley background instead of random baseline (uniform coupling) (ablation)p-SHAP (COLA) · Hotel Bookings, 80% effectnumber of modified features: 7.10 -> 7.01Mixed
apply COLA with p-SHAP to refine counterfactualsoriginal counterfactuals · four datasets, 80% effectshare of original feature changes: 13%-25% of the feature changesImproved
apply COLA with p-SHAP to reach full counterfactual effectoriginal counterfactuals · four datasets, 100% effectshare of original feature changes: 26%-45% of the feature changesImproved
use OT coupling instead of known exact factual-counterfactual alignment (ablation)p-SHAP (COLA) · German Credit MILP benchmarkmodified features vs MILP optimumMixed

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