联合分布感知的反事实解释Shapley值
Joint Distribution-Informed Shapley Values for Sparse Counterfactual Explanations
AI总结：
COLA通过联合分布感知的Shapley值方法，优化反事实解释的特征编辑，减少冗余修改，提升解释的清晰度和实用性。
摘要：
反事实解释（CE）旨在揭示如何通过微小的输入变化翻转模型的预测，但许多方法修改了不必要的更多特征，从而降低清晰度和可操作性。我们引入了COLA，一种模型和生成器无关的后验框架，通过最优传输（OT）在事实和反事实集合之间计算耦合，从而驱动基于Shapley的归因（p-SHAP）以选择最小的编辑集，同时保持目标效应。理论上，OT最小化了事实和反事实结果之间W_1分歧的上界，并且在温和条件下，优化后的反事实不会远离事实比原始更远。实验上，在四个数据集、十二个模型和五个反事实生成器上，COLA仅使用原始特征编辑的26-45%，就实现了相同的目标效应。在小规模基准测试中，COLA表现出接近最优性。
英文摘要：
Counterfactual explanations (CE) aim to reveal how small input changes flip a model's prediction, yet many methods modify more features than necessary, reducing clarity and actionability. We introduce \emph{COLA}, a model- and generator-agnostic post-hoc framework that refines any given CE by computing a coupling via optimal transport (OT) between factual and counterfactual sets and using it to drive a Shapley-based attribution (\emph{$p$-SHAP}) that selects a minimal set of edits while preserving the target effect. Theoretically, OT minimizes an upper bound on the $W_1$ divergence between factual and counterfactual outcomes and that, under mild conditions, refined counterfactuals are guaranteed not to move farther from the factuals than the originals. Empirically, across four datasets, twelve models, and five CE generators, COLA achieves the same target effects with only 26--45\% of the original feature edits. On a small-scale benchmark, COLA shows near-optimality.
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。
