Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation
This addresses the issue of unreliable predictions in regulated or safety-critical domains, such as healthcare, by mitigating model reliance on confounders, though it is incremental as it builds on existing knowledge distillation and explanation methods.
The paper tackles the problem of deep learning models relying on confounding spurious features, which can cause errors in safety-critical domains, by introducing counterfactual knowledge distillation (CFKD) to detect and remove these confounders using human expert feedback, demonstrating effectiveness on synthetic and real-world histopathological datasets.
This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of human expert feedback. Confounders are spurious features that models tend to rely on, which can result in unexpected errors in regulated or safety-critical domains. The paper highlights the benefit of CFKD in such domains and shows some advantages of counterfactual explanations over other types of explanations. We propose an experiment scheme to quantitatively evaluate the success of CFKD and different teachers that can give feedback to the model. We also introduce a new metric that is better correlated with true test performance than validation accuracy. The paper demonstrates the effectiveness of CFKD on synthetically augmented datasets and on real-world histopathological datasets.