AI Paper Atlas

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

Explaining Preferences with Shapley Values

Robert Hu, Siu Lun Chau, Jaime Ferrando Huertas, Dino Sejdinovic

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Shapley value attribution · 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 GPM instead of UPMPreference prediction · SyntheticTest AUC: 0.71_\pm0.01 -> 0.98_{\pm0.00}Improved
Use GPM instead of UPMPreference prediction · ChameleonTest AUC: 0.80_{\pm0.07} -> 0.92_{\pm0.07}Improved
Use GPM instead of UPMPreference prediction · PokémonTest AUC: 0.82_{\pm0.00} -> 0.86_{\pm0.00}Improved
Use context-specific C-GPM instead of UPMPreference prediction · TennisTest AUC: 0.52_{\pm0.02} -> 0.58_{\pm0.02}Improved
Use context-specific C-GPM instead of UPMPreference prediction · WebsiteTest AUC: 0.65_{\pm0.01} -> 0.66_{\pm0.01}No clear effect
Explain pairwise preferences with Pref-SHAP rather than applying SHAP to UPM utilitiesSynthetic pairwise preference explanations · Syntheticrecovery of the designed feature mechanismImproved
Explain pairwise preferences with Pref-SHAP rather than applying SHAP to UPM utilitiesPokémon battle explanations · Pokémonidentification of relevant preference featuresImproved
Explain pairwise preferences with Pref-SHAP rather than applying SHAP to UPM utilitiesChameleon contest explanations · Chameleonconsistency of jaw-length effectImproved
Concatenate both items' features and apply ordinary SHAP instead of using the shared-feature preferential value functionPairwise preference explanations · Syntheticinterpretability of feature attributionsHurt

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