arXiv：cs.LG· Emmanouil Panagiotou, Eirini Ntoutsi·· 4 小时前AI 评分33
FlowCF：用流匹配为混合类型表格数据生成稀疏反事实解释
FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching
AI 导读
FlowCF 是一种模型无关的生成式方法，将反事实解释生成建模为从事实类到目标类的稀疏传输，并用流匹配求解，同时提出混合流算子以支持混合特征类型。在六个基准数据集上，FlowCF 取得最佳数值稀疏性与接近度，仅改变 29% 的数值特征（最佳基线为 89%），位移小 70%。该工作已被 NeurIPS 2026 GDDL Workshop 接收。
正文
Abstract: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.
| Comments: | Accepted at the NeurIPS 2026 Geometric Distributional Deep Learning (GDDL) Workshop |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.08537 [cs.LG] |
| (or arXiv:2610.08537v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08537 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Emmanouil Panagiotou [view email]
[v1]
Tue, 6 Oct 2026 15:27:23 UTC (3,271 KB)
来源：arXiv：cs.LG · arxiv.org