PredDiff: Explanations and interactions from conditional expectations

PredDiff is a model-agnostic, local attribution method that is firmly rooted in probability theory. Its simple intuition is to measure prediction changes while marginalizing features. In this work, we clarify properties of PredDiff and its close connection to Shapley values. We stress important diff...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Artificial intelligence 2022-11, Vol.312, p.103774, Article 103774
Hauptverfasser:	Blücher, Stefan, Vielhaben, Johanna, Strodthoff, Nils
Format:	Artikel
Sprache:	eng
Schlagworte:	Explainable AI Feature attribution Interactions Interpretability Mathematical models Probability theory Shapley values Statistical analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!