MUPAX's feature importance is a weighted average of masked inputs selected for low loss, and its accuracy gains stem from using ground-truth labels during mask selection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MUPAX: Multidimensional Problem Agnostic eXplainable AI
MUPAX's feature importance is a weighted average of masked inputs selected for low loss, and its accuracy gains stem from using ground-truth labels during mask selection.