Machine learning models that incorporate concept learning as an intermediate step in their decision making process can match the performance of black-box predictive models while retaining the ability to explain outcomes in human understandable terms. However, we demonstrate that the concept representations learned by these models encode information beyond the pre-defined concepts, and that natural mitigation strategies do not fully work, rendering the interpretation of the downstream prediction misleading. We describe the mechanism underlying the information leakage and suggest recourse for mitigating its effects.
تحميل البحث