Why Shapley Value and Its Variants Are Useful in Machine Learning (and in Other Applications)

Authors

Laxman Bokati, The University of Texas at El PasoFollow
Olga Kosheleva, The University of Texas at El PasoFollow
Vladik Kreinovich, The University of Texas at El PasoFollow
Nguye Ngoc Thach, Banking University Ho Chi Minh CityFollow

Publication Date

7-1-2022

Comments

Technical Report: UTEP-CS-22-89

Abstract

Shapley value -- a useful way to allocate gains in cooperative games -- has been very successful in machine learning (and in other applications beyond cooperative games). This success is somewhat puzzling, since the usual derivation of the Shapley value is based on requirements like additivity that are natural in cooperative games and but not ents like additivity and is, thus, applicable in the machine learning case as well.