Improving Attribution Methods by Learning Submodular Functions

This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are natural for attribution as they are known to accurately model the principle of diminishing returns. A new formulation for...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-02
Hauptverfasser:	Manupriya, Piyushi, Tarun Ram Menta, Nath, J Saketha, Balasubramanian, Vineeth N
Format:	Artikel
Sprache:	eng
Schlagworte:	Learning Selectivity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!