{"ID":2900848,"CreatedAt":"2026-06-01T05:51:17.9442275Z","UpdatedAt":"2026-06-01T06:23:29.641557848Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2605.30901","arxiv_id":"2605.30901","title":"Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity","abstract":"Counterfactual explanations (CEs) are essential for actionable recourse, yet their reliability is often compromised in low-density regions, where classifiers exhibit high variance. Unlike existing methods that rely on expensive ensemble intersections to define stability, we propose \\textit{DensityFlow}, a generative framework that constructs robust CEs by adhering to the high-confidence data manifold. Specifically, we model the counterfactual generation as continuous-time dynamics parameterized by Neural ODE, guided by a differentiable density score to actively avoid uncertain, low-density areas. This density score is learned via Noise Contrastive Estimation, effectively leveraging a $(K{+}1)$-way discriminator to estimate density ratios. For black-box settings, we introduce a local proxy distillation mechanism that aligns a lightweight surrogate with the target model strictly within the trajectory of CE generation, enabling efficient gradient-based optimization with minimal queries. Experiments demonstrate that \\textit{DensityFlow} achieves superior validity under model multiplicity while significantly reducing query costs compared to ensemble-based baselines. Our implementation is available at https://github.com/G-AILab/DensityFlow.","short_abstract":"Counterfactual explanations (CEs) are essential for actionable recourse, yet their reliability is often compromised in low-density regions, where classifiers exhibit high variance. Unlike existing methods that rely on expensive ensemble intersections to define stability, we propose \\textit{DensityFlow}, a generative fr...","url_abs":"https://arxiv.org/abs/2605.30901","url_pdf":"https://arxiv.org/pdf/2605.30901v1","authors":"[\"Jun Tan\",\"Qing Guo\",\"Zicheng Xu\",\"Jinglin Li\",\"Qi Fang\",\"Ning Gui\"]","published":"2026-05-29T06:36:33Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":612531,"CreatedAt":"2026-06-01T05:51:17.9442275Z","UpdatedAt":"2026-06-01T05:51:17.9442275Z","DeletedAt":null,"paper_id":2900848,"paper_url":"https://arxiv.org/abs/2605.30901","paper_title":"Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity","repo_url":"https://github.com/G-AILab/DensityFlow","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}