Disentangled representations enable a new auditing procedure to identify proxy features and quantify their influence on model outcomes more effectively than prior methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Disentangling Influence: Using Disentangled Representations to Audit Model Predictions
Disentangled representations enable a new auditing procedure to identify proxy features and quantify their influence on model outcomes more effectively than prior methods.