S-CFE：简单反事实解释
S-CFE: Simple Counterfactual Explanations
AI总结：
针对分类器的稀疏流形对齐反事实解释求解难题，本文提出基于加速近端梯度法的S-CFE方法，支持多类分类器与合理性度量，可生成更稀疏的可执行反事实，实验验证其兼具效果与效率。
摘要：
我们研究为分类器寻找最优的稀疏、流形对齐反事实解释的问题。通常，这一问题可被构建为包含多个非凸组件的优化问题，这些组件包括分类器损失函数以及流形对齐（或称“合理性”）指标。而强制实现“稀疏性”（即更短的解释）所带来的额外复杂度，会进一步提升问题的求解难度。现有方法通常针对特定模型和合理性度量设计，依赖凸的ℓ₁正则项来实现稀疏性。本文中，我们采用加速近端梯度（APG）方法求解该标准形式的优化问题，这是一种简单高效的一阶优化流程，能够处理平滑非凸目标函数以及非平滑的ℓₚ（其中0≤p<1）正则项。这使得我们的方法可以无缝适配各类分类器和合理性度量，同时生成稀疏性更强的解。我们的算法仅要求数据流形正则项可微，且支持有界特征范围的盒约束，确保生成的反事实具备“可执行性”。最后，在真实数据集上的实验表明，我们的方法能够有效生成稀疏、流形对齐的反事实解释，同时保持与事实数据的邻近性以及计算效率。
英文摘要：
We study the problem of finding optimal sparse, manifold-aligned counterfactual explanations for classifiers. Canonically, this can be formulated as an optimization problem with multiple non-convex components, including classifier loss functions and manifold alignment (or \emph{plausibility}) metrics. The added complexity of enforcing \emph{sparsity}, or shorter explanations, complicates the problem further. Existing methods often focus on specific models and plausibility measures, relying on convex $\ell_1$ regularizers to enforce sparsity. In this paper, we tackle the canonical formulation using the accelerated proximal gradient (APG) method, a simple yet efficient first-order procedure capable of handling smooth non-convex objectives and non-smooth $\ell_p$ (where $0 \leq p < 1$) regularizers. This enables our approach to seamlessly incorporate various classifiers and plausibility measures while producing sparser solutions. Our algorithm only requires differentiable data-manifold regularizers and supports box constraints for bounded feature ranges, ensuring the generated counterfactuals remain \emph{actionable}. Finally, experiments on real-world datasets demonstrate that our approach effectively produces sparse, manifold-aligned counterfactual explanations while maintaining proximity to the factual data and computational efficiency.
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。
