面向随机森林的可解释模型感知反事实解释
Interpretable Model-Aware Counterfactual Explanations for Random Forest
AI总结：
本文提出一种基于相似性学习的反事实搜索与解释方法，利用 Random Forest 模型表征寻找反事实案例并计算特征重要性，在 MNIST 和 German credit 数据集上生成的解释比 Shapley values 更稀疏且更有用。
摘要：
尽管机器学习模型具有巨大的预测能力，但由于其提供解释的能力有限，它们通常不适用于金融等受监管行业的应用。尽管 Shapley values 等模型无关框架已被证明方便且受欢迎，但它们很少与通常寻求的因果解释类型相一致。反事实基于案例的解释（即告知个体需要改变哪些情况才能导致结果发生变化）可能更直观且更具可操作性。然而，寻找合适的反事实案例是一个悬而未决的挑战，解释哪些特征对结果变化最为关键同样如此。在此，我们以相似性学习的形式提出反事实搜索与解释问题，利用 Random Forest 预测模型自身学习到的表征。一旦找到反事实，解释的特征重要性将作为从原始实例到达该反事实所跨越的 Random Forest 分区的函数进行计算。我们在 MNIST 手绘数字数据集和 German credit 数据集上验证了该方法，发现它生成的解释比 Shapley values 更稀疏且更有用。
英文摘要：
Despite their enormous predictive power, machine learning models are often unsuitable for applications in regulated industries such as finance, due to their limited capacity to provide explanations. While model-agnostic frameworks such as Shapley values have proved to be convenient and popular, they rarely align with the kinds of causal explanations that are typically sought after. Counterfactual case-based explanations, where an individual is informed of which circumstances would need to be different to cause a change in outcome, may be more intuitive and actionable. However, finding appropriate counterfactual cases is an open challenge, as is interpreting which features are most critical for the change in outcome. Here, we pose the question of counterfactual search and interpretation in terms of similarity learning, exploiting the representation learned by the random forest predictive model itself. Once a counterfactual is found, the feature importance of the explanation is computed as a function of which random forest partitions are crossed in order to reach it from the original instance. We demonstrate this method on both the MNIST hand-drawn digit dataset and the German credit dataset, finding that it generates explanations that are sparser and more useful than Shapley values.
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。
