CounterFlowNet: 从最小变化到有意义的反事实解释
CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations
AI总结：
CounterFlowNet通过条件生成流网络生成高质量反事实解释，支持稀疏修改和异质特征，满足用户约束条件。
摘要：
反事实解释（CFs）通过识别对输入特征做出最小变化以改变模型输出来提供人类可解释的模型预测洞察。然而，现有方法在生成多个高质量解释方面存在困难，这些解释需要（1）只影响少量特征，（2）适用于具有异质特征的表格数据，（3）与用户定义的约束一致。我们提出了CounterFlowNet，一种生成方法，将CF生成公式化为使用条件生成流网络（GFlowNet）的顺序特征修改。CounterFlowNet被训练以根据用户指定的奖励函数采样CFs，该奖励函数可以编码关键CF需求：有效性、稀疏性、接近性和合理性，鼓励高质量的解释。顺序公式化产生高度稀疏的修改，而统一的操作空间无缝支持连续和分类特征。此外，可操作性约束，如特征的不可变性和单调性，可以通过操作遮蔽在推理时强制执行，而无需重新训练。在八个数据集上使用两种评估协议的实验表明，CounterFlowNet在有效性、稀疏性、合理性和多样性之间实现了优越的权衡，并完全满足给定的约束。
英文摘要：
Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to generate multiple high-quality explanations that (1) affect only a small portion of the features, (2) can be applied to tabular data with heterogeneous features, and (3) are consistent with the user-defined constraints. We propose CounterFlowNet, a generative approach that formulates CF generation as sequential feature modification using conditional Generative Flow Networks (GFlowNet). CounterFlowNet is trained to sample CFs proportionally to a user-specified reward function that can encode key CF desiderata: validity, sparsity, proximity and plausibility, encouraging high-quality explanations. The sequential formulation yields highly sparse edits, while a unified action space seamlessly supports continuous and categorical features. Moreover, actionability constraints, such as immutability and monotonicity of features, can be enforced at inference time via action masking, without retraining. Experiments on eight datasets under two evaluation protocols demonstrate that CounterFlowNet achieves superior trade-offs between validity, sparsity, plausibility, and diversity with full satisfaction of the given constraints.
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。
