在数据有限时重建黑箱模型，用反事实样本提升准确性与公平性审计能力。
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
- 基于反事实样本构建水仙花原型，无需在线查询即可重建模型行为
- 在低样本下保持高保真度，对抗决策边界偏移和过拟合
- 适合缺乏访问权限的第三方公平性审计场景
反事实解释（CFs）通过识别导致模型输出改变的最小输入变化，帮助理解机器学习模型。近期研究表明，其可用于重建黑箱模型，支持对不透明决策系统的公平性与问责性第三方审计。然而，基于CF的重建可能受决策边界偏移、过拟合及需在线查询目标平台等限制影响。我们提出在数据受限和访问受限条件下，基于水仙花重心原型的反事实感知模型重建方法RECAST。该方法通过将反事实样本作为两类中虽不具代表性但信息丰富的样本，有效缓解决策边界偏移问题，在低样本情形下仍能保持高代理模型保真度，且无需重建期间在线访问。为增强公平性审计能力，本方法支持系统化的群体公平性诊断。在真实世界数据集和多种设置下的实验表明，RECAST在高保真度、高查询效率方面表现优异，并在访问受限和噪声环境下仍具稳定性。
原文摘要 · Abstract (English)
Counterfactual explanations (CFs) help understand machine learning models by identifying minimal input changes that would lead to alternative model outcomes. Recent work demonstrates their utility for reconstructing black-box models, enabling third-party auditing of opaque decision systems for fairness and accountability. Still, CF-based reconstruction may suffer from decision boundary shifts, overfitting, and restrictive assumptions requiring online query access to target platforms. We propose REconstruction via Counterfactual-Aware waSserstein opTimization (RECAST) under limited data and restricted access, a behavioral surrogate model based on Wasserstein barycentric prototypes. Our approach addresses decision boundary shifts by incorporating CFs as informative, though less representative, samples for both classes, maintaining high surrogate fidelity in low-sample regimes without requiring online access during reconstruction. To enhance fairness auditing, our method enables systematic group fairness diagnostics. Experiments on real-world datasets and various setups show that RECAST effectively achieves high fidelity and query efficiency, as well as stable results even when the access is limited and noisy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。