为深度学习模型添加可微分公平层，确保输出结果满足指定公平性标准。
Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning
- 在模型输出层加入可微分优化层，强制实现输出公平性
- 提出在线对偶算法，支持小批量流式预测并保证整体公平性
- 适用于需要严格公平性保障的决策类深度学习任务
传统的可微分优化层通常用于预测-优化框架，即神经网络估计参数后作为下游优化问题的固定输入。本文提出“公平层”概念：一种附加于模型输出层的可微分优化层，可确保将该层集成进神经网络时，满足特定输出均等性要求。此外，我们设计了一种在线原始-对偶推理算法，可在任意小批量的流式预测中提供可证明的聚合公平性保障，避免传统按批次约束过于严苛的问题。数值实验验证了公平层及其算法的有效性，理论分析刻画了该层在训练和反向传播过程中的可微性和稳定性。相关代码已公开于GitHub（https://github.com/dtroxell19/FairDL-ICML-2026.git），Python包文档见：https://dtroxell19.github.io/fairness_training/。
原文摘要 · Abstract (English)
Differentiable optimization layers are traditionally integrated in predict-then-optimize frameworks where a neural model estimates parameters that subsequently serve as fixed inputs to downstream decision-making optimization problems. In this work, we introduce the concept of a "fairness layer": a differentiable optimization layer appended to a model's output layer that guarantees a chosen notion of output parity is satisfied when integrated into a neural network. Additionally, we introduce an online primal-dual inference algorithm that provides provable aggregate fairness guarantees for streaming predictions with arbitrarily small batch sizes, where traditional per-batch constraints become overly restrictive. Numerical experiments demonstrate the effectiveness of the fairness layer and associated algorithm, and theoretical analysis characterizes the layer's differentiability and stability properties during model training and backpropagation. Our code for these experiments is publicly available on GitHub (https://github.com/dtroxell19/FairDL-ICML-2026.git) and our public Python package documentation can be found online: https://dtroxell19.github.io/fairness_training/.
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。