CountARFactuals——利用对抗随机森林生成合理的、模型无关的反事实解释
CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forests
AI总结：
本文提出CountARFactuals，利用对抗随机森林以模型无关方式高效生成数据流形内的合理反事实解释，并自然支持混合数据与稀疏性约束。
摘要：
反事实解释通过指出本可导致另一种期望结果的情形来阐明算法决策。通过深入了解模型行为，反事实解释向用户提示可能采取的行动，并为质疑决策提供依据。作为实现这些目标的关键因素，反事实必须具有合理性，即在数据流形内描述现实的替代情形。本文利用近期开发的一种生成建模技术——对抗随机森林（ARFs）——以模型无关的方式高效生成合理的反事实。ARFs可用作合理性度量，或直接生成反事实解释。我们基于ARF的方法克服了现有旨在生成合理解释的方法的局限：它易于训练且计算效率极高，可自然处理连续数据和分类数据，并允许以直接方式整合稀疏性等附加需求。
英文摘要：
Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds for contesting decisions. As a crucial factor in achieving these goals, counterfactuals must be plausible, i.e., describing realistic alternative scenarios within the data manifold. This paper leverages a recently developed generative modeling technique -- adversarial random forests (ARFs) -- to efficiently generate plausible counterfactuals in a model-agnostic way. ARFs can serve as a plausibility measure or directly generate counterfactual explanations. Our ARF-based approach surpasses the limitations of existing methods that aim to generate plausible counterfactual explanations: It is easy to train and computationally highly efficient, handles continuous and categorical data naturally, and allows integrating additional desiderata such as sparsity in a straightforward manner.
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。
