使用反事实解释的模型重构：基于多面体理论的视角
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
AI总结：
本文基于多面体理论分析了反事实解释在模型重构中的作用，推导出重构误差与反事实查询数量的理论关系，提出反事实钳制攻击（CCA）策略，通过独特损失函数训练替代模型，缓解决策边界偏移并提升模型预测保真度。
摘要：
反事实解释提供了通过最小输入扰动获得有利模型结果的方法。然而，反事实解释也可被用于重构模型，方法是通过策略性地训练一个替代模型，使其给出与原始（目标）模型相似的预测。在本研究中，我们分析了如何通过进一步利用反事实非常接近决策边界这一事实，来改进使用反事实的模型重构。我们的主要贡献是利用多面体理论，推导出模型重构误差与所需反事实查询数量之间的新颖理论关系。基于理论分析，我们提出了一种模型重构策略，称为反事实钳制攻击（CCA），该策略使用独特的损失函数训练替代模型，该函数对反事实的处理不同于普通实例。当反事实被视为普通实例时，现有模型重构方法会出现决策边界偏移的相关问题，我们的方法也缓解了这一问题。实验结果表明，我们的策略提高了多个数据集上目标模型与替代模型预测之间的保真度。
英文摘要：
Counterfactual explanations provide ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be leveraged to reconstruct the model by strategically training a surrogate model to give similar predictions as the original (target) model. In this work, we analyze how model reconstruction using counterfactuals can be improved by further leveraging the fact that the counterfactuals also lie quite close to the decision boundary. Our main contribution is to derive novel theoretical relationships between the error in model reconstruction and the number of counterfactual queries required using polytope theory. Our theoretical analysis leads us to propose a strategy for model reconstruction that we call Counterfactual Clamping Attack (CCA) which trains a surrogate model using a unique loss function that treats counterfactuals differently than ordinary instances. Our approach also alleviates the related problem of decision boundary shift that arises in existing model reconstruction approaches when counterfactuals are treated as ordinary instances. Experimental results demonstrate that our strategy improves fidelity between the target and surrogate model predictions on several datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
