Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations

About

While the need for interpretable machine learning has been established, many common approaches are slow, lack fidelity, or hard to evaluate. Amortized explanation methods reduce the cost of providing interpretations by learning a global selector model that returns feature importances for a single instance of data. The selector model is trained to optimize the fidelity of the interpretations, as evaluated by a predictor model for the target. Popular methods learn the selector and predictor model in concert, which we show allows predictions to be encoded within interpretations. We introduce EVAL-X as a method to quantitatively evaluate interpretations and REAL-X as an amortized explanation method, which learn a predictor model that approximates the true data generating distribution given any subset of the input. We show EVAL-X can detect when predictions are encoded in interpretations and show the advantages of REAL-X through quantitative and radiologist evaluation.

Neil Jethani, Mukund Sudarshan, Yindalon Aphinyanaphongs, Rajesh Ranganath• 2021

Related benchmarks

TaskDatasetResultRank
ClassificationLung
ACC93.27
96
ClassificationAdult
Accuracy36.48
86
ClassificationTOX_171
Accuracy90.79
78
ClassificationGLI_85
Accuracy83.24
78
ClassificationColon
Accuracy76.75
78
ClassificationALLAML
Accuracy84.16
72
ClassificationSMK_CAN_187
Accuracy56.48
72
ClassificationHDLSS Datasets Summary
Average Rank12.75
66
ClassificationProstate_GE
Accuracy86.75
64
ClassificationARCENE
Accuracy77.3
60
Showing 10 of 21 rows

Other info

Follow for update