提出可生成合理且高效反事实解释的新算法，帮助用户理解并改变不公决策。
P$^2$CE: Model-Agnostic Plausible Pareto-Optimal Counterfactual Explanations
- 用孤立森林检测异常，确保解释符合数据分布
- 结合SHAP值实现快速计算，不依赖具体模型
- 在3个数据集上表现更优，兼顾质量与效率
机器学习在社会应用中的普及引发了公平性与透明度的担忧，催生了反事实解释。这类解释帮助个人理解并可能改变贷款、求职等场景中的不利决定，通过提供可操作的输入特征调整建议。现有方法常难以平衡可行性、合理性与计算效率。为此，我们提出P²CE算法，生成合理且帕累托最优的反事实解释，为用户提供多样化的可行性权衡方案。P²CE采用辅助孤立森林异常检测器，确保解释符合数据分布，并利用SHAP值实现短时间内的最优结果，适用于任意底层模型。在三个数据集上的实证评估表明，该算法在解的质量和计算效率方面均优于现有技术。
原文摘要 · Abstract (English)
The increasing use of machine learning algorithms in social applications has raised concerns about fairness and transparency, leading to the development of counterfactual explanations. These explanations supports individuals to understand and potentially alter unfavorable decisions in areas such as loan applications, job selections, and more, by providing actionable changes to input features that would lead to a desired outcome. Existing methods often struggle to balance feasibility, plausibility, and computational efficiency. To address this, we introduce P$^2$CE, an algorithm for generating plausible Pareto-optimal counterfactual explanations, offering users a diverse set of optimal trade-offs between different notions of feasibility. P$^2$CE employs an auxiliary isolation forest outlier detector to ensure that explanations are in accordance with the data distribution and leverages SHAP values to obtain optimal results with short computing times, regardless of the underlying model. Our algorithm was empirically evaluated on three datasets, demonstrating superior performance in terms of both solution quality and computational efficiency compared to related techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。