FCx：一种寻找可行反事实解释的算法
FCx: An algorithm for finding Feasible Counterfactual Explanations
- National and Kapodistrian University of Athens（雅典国立卡波季斯特里安大学）
- Athens University of Economics and Business（雅典经济与商业大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出FCx算法，通过硬/软约束和修改的VAE，首次高效生成可行、逼真且低成本的反事实解释，在四个数据集上达到最先进性能。
AI中文摘要：
反事实（CF）解释识别改变输入分类的变化。虽然现有方法能产生逼真且低成本的CF，但它们往往无法确保可行性，通过建议非建设性的修改或与未来变化不兼容（例如，改变个体的种族以获得工作机会）。我们引入了一种明确强制可行性的CF解释的改进。我们的方法是第一个高效生成逼真、低成本且可行的CF的方法。我们同时容纳由领域知识用户指定的硬可行性约束，以及通过因果推断从数据集中自动推断的软可行性约束。我们的方法，可行反事实解释（FCx），基于一个通过多因子损失函数优化的改进变分自编码器（VAE）。我们根据值的绝对变化（邻近性）以及改变的特征数量（稀疏性）来衡量变化的成本，而逼真性则基于用于密度估计的LOF来衡量，确保CF位于高密度区域。在四个公开数据集上的大量实验表明，我们的方法在多个指标上达到最先进的性能，同时保证可行性。
英文摘要：
Counterfactual (CF) explanations identify changes that alter an input's classification. While existing methods produce realistic and low-cost CFs, they often fail to ensure feasibility, by suggesting non-constructive modifications or incompatible with future changes (e.g., changing an individual's race to secure a job offer). We introduce a refinement of CF explanations that explicitly enforces feasibility. Our approach is the first to efficiently generate CFs that are realistic, low-cost and feasible. We accommodate both hard feasible constraints, specified by domain knowledge users, and soft feasible constraints, inferred automatically via causal inference from the dataset. Our method, Feasible Counterfactual Explanations (FCx), is based on a modified Variational Autoencoder (VAE) optimized with a multi-factor loss function. We measure the cost of a change based on the absolute change in values (proximity) as well as the number of features changed (sparsity) while realism is measured based on the LOF for density estimation, guaranteeing that CFs reside in densely populated regions. Extensive experiments on four public datasets show that our approach matches state-of-the-art performance across multiple metrics while guaranteeing feasibility.
