用反事实图分析时间序列分类器的类间转换关系，发现高准确率边界反而难被编辑跨越。
Counterfactual Transition Graphs: Evaluating Cross-Class Transition Quality
- 构建类间反事实转换图，以原型检索方式量化跨类转换可靠性。
- 在六类手势任务中发现：准确率高的类别间转换反而最不可靠（斯皮尔曼ρ=-0.37）。
- 适用于任意反事实解释方法对比，尤其适合研究编辑是否脱离数据流形。
时间序列分类器的反事实解释通常逐例评估：如何最小修改使单个窗口预测翻转？我们提出更深层的问题：分类器内部的类之间如何相互连接？为此，我们构建反事实转换图（CGT），其中每个节点代表一个类别，边权重表示在邻近感知检索下从一个原型到另一个的反事实可靠性。在六类手部动作任务中，我们生成的CGT揭示了非平凡拓扑结构，该结构无法由二值混淆矩阵预测：反事实可达性与分类器准确率不一致，甚至相反（15对组合中斯皮尔曼ρ = -0.37）。即，分类器最自信分离的边界，恰恰是最难通过分布内编辑跨越的。该框架方法无关，可兼容任意反事实解释器；当前用于对比基于替换与基于梯度的反事实方法：后者可通过脱离数据流形到达几乎所有类别，而前者保持在流形上，却在刚性边界处失败。
原文摘要 · Abstract (English)
Counterfactual (CF) explanations for time-series classifiers are usually evaluated one example at a time: what minimal edit flips this single window's prediction? We argue that the more informative question for diagnostic interpretability is structural: how does the classifier connect its own classes to each other? We propose a counterfactual transition graph (CGT) in which each node is a class and each edge weight is the CF reliability of the transition from one prototype to another under a proximity aware retrieval sweep. On a six-class hand-movement task, we induce a CGT that reveals a non-trivial topology, which is not predicted by the binary confusion matrix: it shows that counterfactual reachability does not align with classifier accuracy and even runs counter to it (Spearman $ρ=-0.37$ over the 15 pairs), i.e. the boundaries the classifier separates most confidently are among those an in-distribution edit can least often cross. Our framework is method agnostic, i.e. any CF-explainers can be used. Presently, we use it to juxtapose replacement-based CFs with gradient-based CFs; gradient-based methods reach almost any class by stepping off the data manifold, while replacement-based methods stay on it and fail on precisely the rigid boundaries.
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。