Towards learning to explain with concept bottleneck models: mitigating information leakage

Abstract

Concept bottleneck models perform classification by first predicting which of a list of human provided concepts are true about a datapoint. Then a downstream model uses these predicted concept labels to predict the target label. The predicted concepts act as a rationale for the target prediction. Model trust issues emerge in this paradigm when soft concept labels are used: it has previously been observed that extra information about the data distribution leaks into the concept predictions. In this work we show how Monte-Carlo Dropout can be used to attain soft concept predictions that do not contain leaked information.