With the increased deployment of machine learning models in various real-world applications, researchers and practitioners alike have emphasized the need for explanations of model behaviour. To this end, two broad strategies have been outlined in prior literature to explain models. Post hoc explanation methods explain the behaviour of complex black-box models by identifying features critical to model predictions; however, prior work has shown that these explanations may not be faithful, in that they incorrectly attribute high importance to features that are unimportant or non-discriminative for the underlying task. Inherently interpretable models, on the other hand, circumvent these issues by explicitly encoding explanations into model architecture, meaning their explanations are naturally faithful, but they often exhibit poor predictive performance due to their limited expressive power. In this work, we identify a key reason for the lack of faithfulness of feature attributions: the lack of robustness of the underlying black-box models, especially to the erasure of unimportant distractor features in the input. To address this issue, we propose Distractor Erasure Tuning (DiET), a method that adapts black-box models to be robust to distractor erasure, thus providing discriminative and faithful attributions. This strategy naturally combines the ease of use of post hoc explanations with the faithfulness of inherently interpretable models. We perform extensive experiments on semi-synthetic and real-world datasets and show that DiET produces models that (1) closely approximate the original black-box models they are intended to explain, and (2) yield explanations that match approximate ground truths available by construction. Our code is made public at https://github.com/AI4LIFE-GROUP/DiET.

翻译：随着机器学习模型在各类实际应用中的广泛部署，研究人员和从业者越来越强调对模型行为进行解释的需求。为此，现有文献概括出两大策略来解释模型。事后解释方法通过识别对模型预测至关重要的特征来解释复杂黑箱模型的行为；然而，先前研究表明这些解释可能不忠实——它们会错误地将高重要性归因于对底层任务而言不重要或非判别性的特征。相比之下，内在可解释模型通过将解释显式编码到模型架构中来规避这些问题，这意味着其解释自然具备忠实性，但受限于表达能力而往往预测性能较差。在本工作中，我们识别出特征归因缺乏忠实性的关键原因：底层黑箱模型缺乏鲁棒性，尤其对输入中不重要的干扰特征被擦除的情况缺乏稳健性。为解决该问题，我们提出干扰擦除微调（DiET）方法，该方法通过适配黑箱模型使其对干扰特征擦除具有鲁棒性，从而提供具备判别性和忠实性的归因。该策略自然结合了事后解释的易用性与内在可解释模型的忠实性。我们在半合成数据集和真实世界数据集上进行了大量实验，结果表明DiET生成的模型：（1）高度逼近其旨在解释的原始黑箱模型；（2）产生的解释与通过构造获得的近似真实情况相匹配。我们的代码已公开于https://github.com/AI4LIFE-GROUP/DiET。