Data-centric Prediction Explanation via Kernelized Stein Discrepancy

Existing example-based prediction explanation methods often bridge test and training data points through the model's parameters or latent representations. While these methods offer clues to the causes of model predictions, they often exhibit innate shortcomings, such as incurring significant co...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Sarvmaili, Mahtab, Sajjad, Hassan, Wu, Ga
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!