可重用MLOps流水线中的伦理与可解释性AI
Ethical and Explainable AI in Reusable MLOps Pipelines
AI总结：
本文提出了一种整合伦理和可解释性AI的MLOps框架，通过自动化公平性控制和可解释性特征，在生产环境中实现公平性与预测效用的平衡。
摘要：
本文介绍了一个统一的机器学习操作（MLOps）框架，通过在整个机器学习生命周期中强制实施公平性、可解释性和治理原则，将伦理人工智能原则引入实际应用。所提出的方法通过降低人口平差差异（DPD）从0.31降至0.04而不进行模型重新训练，且跨数据集验证在Statlog心脏病数据集上实现了曲线下面积（AUC）为0.89。该框架在所有部署中保持公平性指标在操作限制内。如果DPD超过0.05或验证集上的等化几率（EO）超过0.05，则模型部署被阻止。部署后，如果30天Kolmogorov-Smirnov漂移统计量超过0.20，则会自动触发重新训练。在生产环境中，系统持续实现了DPD<=0.05和EO<=0.03，同时KS统计量保持<=0.20。决策曲线分析显示在10到20个百分点的运行范围内具有正的净收益，表明缓解后的模型在保持预测效用的同时满足公平性约束。这些结果表明，自动化公平闸门和可解释性特征可以成功部署在生产环境中，而不会影响操作流程，为组织提供了一种实用且可信的方法，以在多样化的数据集和操作环境中实施伦理、透明和可信的AI。
英文摘要：
This paper introduces a unified machine learning operations (MLOps) framework that brings ethical artificial intelligence principles into practical use by enforcing fairness, explainability, and governance throughout the machine learning lifecycle. The proposed method reduces bias by lowering the demographic parity difference (DPD) from 0.31 to 0.04 without model retuning, and cross-dataset validation achieves an area under the curve (AUC) of 0.89 on the Statlog Heart dataset. The framework maintains fairness metrics within operational limits across all deployments. Model deployment is blocked if the DPD exceeds 0.05 or if equalized odds (EO) exceeds 0.05 on the validation set. After deployment, retraining is automatically triggered if the 30-day Kolmogorov-Smirnov drift statistic exceeds 0.20. In production, the system consistently achieved DPD <= 0.05 and EO <= 0.03, while the KS statistic remained <= 0.20. Decision-curve analysis indicates a positive net benefit in the 10 to 20 percent operating range, showing that the mitigated model preserves predictive utility while satisfying fairness constraints. These results demonstrate that automated fairness gates and explainability artefacts can be successfully deployed in production without disrupting operational flow, providing organizations with a practical and credible approach to implementing ethical, transparent, and trustworthy AI across diverse datasets and operational settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
