We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each expert explains a subset of data using First Order Logic (FOL). While explaining a sample, the FOL from biased BB-derived MoIE detects the shortcut effectively. Finetuning the BB with Metadata Normalization (MDN) eliminates the shortcut. The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut. Our experiments show that MoIE does not hurt the accuracy of the original BB and eliminates shortcuts effectively.

翻译：我们利用基于概念的可解释模型来缓解捷径学习问题。现有方法缺乏可解释性。从黑盒模型（Blackbox）出发，我们迭代地提取出一个混合可解释专家（MoIE）和一个残差网络。每个专家使用一阶逻辑（FOL）解释部分数据子集。在解释样本时，来自有偏黑盒模型衍生的MoIE的一阶逻辑能够有效检测捷径。通过元数据归一化（MDN）微调黑盒模型，可以消除捷径。来自微调后黑盒模型衍生的MoIE的一阶逻辑验证了捷径的消除。实验表明，MoIE不会损害原始黑盒模型的准确性，并能有效消除捷径。