发表机构
Freie Universität Berlin; University of the Bundeswehr Munich（柏林自由大学; 慕尼黑联邦国防军大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FlowCF提出一种基于流匹配的模型无关生成方法，通过混合流算子和门控网络优化稀疏传输，在六个基准数据集上实现数值特征稀疏性与邻近性的显著提升。
AI 中文摘要
在可解释人工智能（XAI）领域，反事实（CF）解释通过建议对输入进行更改以获得更有利的结果来解释模型的决策。为了在实践中发挥作用，这样的解释应该更改尽可能少的特征，并且更改幅度尽可能小，这些属性被称为稀疏性和邻近性。我们观察到，现有方法在这方面仍然有限，尤其是对于数值特征，无论它们是模型无关且摊销的，还是基于梯度且完全访问模型的。在本文中，我们提出了FlowCF，一种模型无关的生成方法，将CF生成视为从事实类到目标类的稀疏传输。我们使用流匹配来解决这种传输，并通过一种新颖的混合流算子将其扩展到混合特征类型，并利用由此产生的几何结构，通过一个门控网络来优化稀疏性，该网络最小化传输改变的特征数量。在六个基准数据集上的大量实验表明，FlowCF产生了最佳的数值稀疏性和邻近性，在最佳基线改变89%的数值特征的情况下，仅改变了29%的数值特征，位移减少了70%，同时在其他期望属性上保持可比性。
英文摘要
In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would lead to a more favourable outcome. To be useful in practice, such an explanation should change few features and change them as little as possible, properties known as sparsity and proximity. We observe that existing methods remain limited in this respect, especially for numerical features, whether they are model-agnostic and amortised, or gradient-based with full access to the model. In this paper, we propose FlowCF, a model-agnostic generative method that frames CF generation as sparse transport from the factual to the target class. We solve this transport with flow matching, which we extend to mixed feature types with a novel mixed flow operator, and exploit the resulting geometry to optimise for sparsity through a gating network that minimises the number of features the transport changes. Extensive experiments on six benchmark datasets demonstrate that FlowCF produces the best numerical sparsity and proximity, changing 29% of the numerical features where the best baseline changes 89%, at 70% smaller displacement, while remaining comparable on the other desiderata.
CommentsAccepted at the NeurIPS 2026 Geometric Distributional Deep Learning (GDDL) Workshop
