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

Laxman Bokati, The University of Texas at El Paso
Olga Kosheleva, The University of Texas at El Paso
Vladik Kreinovich, The University of Texas at El Paso
Nguyen Ngoc Thach, Banking University Ho Chi Minh City

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.