P$^2$CE: 模型无关的可行帕累托最优反事实解释
P$^2$CE: Model-Agnostic Plausible Pareto-Optimal Counterfactual Explanations
AI总结：
提出P$^2$CE算法，利用隔离森林异常检测和SHAP值，生成可行且帕累托最优的反事实解释，平衡可行性、合理性和计算效率。
摘要：
机器学习算法在社会应用中的日益普及引发了对公平性和透明度的担忧，从而推动了反事实解释的发展。这些解释通过提供可操作的输入特征更改，帮助个人理解并可能改变在贷款申请、工作选择等领域的不利决策。现有方法往往难以平衡可行性、合理性和计算效率。为此，我们提出了P$^2$CE，一种生成可行帕累托最优反事实解释的算法，为用户提供不同可行性概念之间的多样化最优权衡。P$^2$CE使用辅助隔离森林异常检测器确保解释符合数据分布，并利用SHAP值在短时间内获得最优结果，与底层模型无关。我们在三个数据集上进行了实证评估，结果表明，与相关技术相比，该算法在解决方案质量和计算效率方面均表现出优越性能。
英文摘要：
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.
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。
