Abstract:Counterfactual explanations improve the actionable interpretability of machine learning models by identifying minimal changes required to achieve a desired outcome. However, existing methods often neglect dependencies among features, which can lead to unrealistic or impractical modifications. This limitation reduces the usefulness of counterfactual explanations in real-world decision-support systems.
Motivated by applications in cybersecurity for email marketing, we propose DANCE (Diverse, Actionable, and Knowledge-Constrained Explanations), a method for generating counterfactuals that incorporate feature dependencies and domain constraints. DANCE models relationships between features using linear and probabilistic structures that can be learned from data or specified by experts. These dependencies are enforced during the search process to improve plausibility and feasibility.
The method jointly optimizes plausibility, diversity, proximity, and sparsity within a unified objective. We evaluate DANCE on 140 datasets from OpenML and demonstrate that it achieves competitive or superior performance compared to existing approaches across multiple evaluation criteria. Additionally, we validate the method in a real-world industrial setting in collaboration with an email marketing platform, showing that it produces domain-consistent and actionable recommendations.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2511.20236 [cs.AI] |
| (or arXiv:2511.20236v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2511.20236 arXiv-issued DOI via DataCite |
From: Szymon Bobek [view email]
[v1]
Tue, 25 Nov 2025 12:09:36 UTC (500 KB)
[v2]
Fri, 28 Nov 2025 07:20:29 UTC (500 KB)
[v3]
Mon, 25 May 2026 10:50:11 UTC (383 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。