提出公平性约束下的提升算法，量化了公平训练带来的准确率损失。
Projected Boosting with Fairness Constraints: Quantifying the Cost of Fair Training Distributions
- 通过投影重构训练分布，实现公平性约束下的提升学习
- 理论证明收敛速度受公平性代价项影响，明确权衡关系
- 实验验证理论预测，训练稳定且兼顾公平与精度
提升算法具有强理论保障：当弱学习器保持正边时，AdaBoost可实现指数损失的几何下降。本文研究如何在保持可分析训练动态的前提下，将群体公平性约束融入提升算法。所提出的FairBoost方法，将集成模型产生的指数权重分布投影到满足公平性约束的凸分布集上（作为重加权的代理），然后在此公平分布上训练弱学习器。关键理论洞见是：对训练分布的投影会降低弱学习器的有效边，其降幅由投影的KL散度控制。我们证明了指数损失上界，收敛速率取决于弱学习器边减去一个‘公平性代价’项δ_t = √(KL(w^t || q^t)/2)。该结果直接量化了提升过程中准确率与公平性的权衡。在标准基准上的实验验证了理论预测，并展示了具备稳定训练曲线的竞争性公平-准确权衡。
原文摘要 · Abstract (English)
Boosting algorithms enjoy strong theoretical guarantees: when weak learners maintain positive edge, AdaBoost achieves geometric decrease of exponential loss. We study how to incorporate group fairness constraints into boosting while preserving analyzable training dynamics. Our approach, FairBoost, projects the ensemble-induced exponential-weights distribution onto a convex set of distributions satisfying fairness constraints (as a reweighting surrogate), then trains weak learners on this fair distribution. The key theoretical insight is that projecting the training distribution reduces the effective edge of weak learners by a quantity controlled by the KL-divergence of the projection. We prove an exponential-loss bound where the convergence rate depends on weak learner edge minus a "fairness cost" term $δ_t = \sqrt{\mathrm{KL}(w^t \| q^t)/2}$. This directly quantifies the accuracy-fairness tradeoff in boosting dynamics. Experiments on standard benchmarks validate the theoretical predictions and demonstrate competitive fairness-accuracy tradeoffs with stable training curves.
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。