用梯度SHAP和隐函数定理，让工业优化推荐变得可解释。
Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation
- 结合隐函数定理与SHAP，高效计算参数敏感性。
- 22维特征下，速度比核SHAP快40倍，相关性超0.99。
- 生成实时自然语言解释，适合工厂工程师使用。
自动化优化在工业流程中日益普及，但算法设计者与操作人员之间仍存在信任鸿沟。类似SHAP的可解释AI方法已革新机器学习预测的可解释性，优化输出亦可从中受益。本文提出一种融合隐函数定理（IFT）敏感性分析、SHAP归因与大语言模型（LLM）叙事生成的方法，为操作员提供定制化解释。利用IFT从最优性条件直接计算参数敏感性∂p*/∂x，实现高效的梯度SHAP计算。针对含22个特征的工业高压辊磨机（HPGR）控制优化问题，所得归因结果与核SHAP相关性超过0.99，且提速逾40倍，支持实时自然语言解释。我们在工业场景中验证了该方法，并收集了领域专家对生成解释的反馈。
原文摘要 · Abstract (English)
Automated optimisation is increasingly adopted in industrial processes, yet a trust gap persists between engineers who design these algorithms and operators who must act on their recommendations. Explainable AI methods like SHAP (SHapley Additive exPlanations) have transformed interpretability for machine learning predictions; optimisation outputs could benefit from similar techniques. We present an approach that integrates Implicit Function Theorem (IFT) based sensitivity analysis with SHAP attribution and narrative generation via Large Language Models (LLM), producing explanations tailored for operators. Our approach leverages IFT to compute exact parameter sensitivities $\partial p^*/\partial x$ from the optimality conditions, enabling efficient GradientSHAP computation. For an industrial High Pressure Grinding Roll (HPGR) control optimisation problem with 22 features, we achieve equivalent SHAP attributions (correlation $>$0.99 with KernelSHAP) with over 40$\times$ speedup, enabling real-time natural language explanations. We validate on industrial scenarios and present feedback from domain experts on generated explanations.
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。