AI Paper Atlas

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

Shapley Value Approximation Based on k-Additive Games

Guilherme Dean Pelegrina, Patrick Kolpaczki, Eyke Hüllermeier

AAAI 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Shapley value attribution · 1 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
raise surrogate additivity degree k from 1 or 2 to 3 or 4 (ablation)SVAkADD · Titanic, Wine, Adult, ImageNet, Big Five, Breast CancerMSE vs exact Shapley valuesImproved
use k=3 rather than k=4 (ablation)SVAkADD · six feature-explanation datasetsMSE vs budgetMixed
fit k-additive surrogate game instead of Monte Carlo mean estimates (vs KernelSHAP)SVAkADD · Adult, Big Five, ImageNet, WineMSE vs budgetImproved
fit k-additive surrogate game instead of KernelSHAPSVAkADD · Titanic, Breast CancerMSE vs budgetHurt

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