提出兼顾公平与隐私的模型优化方法，提升弱势群体性能。
Adaptive Sampling and Clipping for Private Worst-Case Group Optimization
- 动态调整各群体梯度采样率和裁剪阈值，自适应重加权训练目标。
- 在保护隐私前提下，显著提升最差群体准确率，整体平均精度不变。
- 适合注重公平性与数据隐私的医疗、金融等敏感场景应用。
机器学习在以人为本的任务中被广泛接受的关键在于其公平性——对不同社会群体应表现一致。同时，用户数据隐私也至关重要。尽管已有方法分别解决公平性（如最差群体优化）和隐私性（如差分隐私SGD），但二者常相互冲突，尚无实用方案能同时满足。本文提出ASC（自适应采样与裁剪的最差群体优化）算法，动态控制各群体梯度的采样率与裁剪阈值，从而在保持低噪声以保障隐私的同时，增强对难学群体的训练权重。实验表明，相比以往方法，ASC显著提升了最差群体准确率，且未牺牲整体平均准确率。
原文摘要 · Abstract (English)
A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they should work comparably well for individuals from different societal groups. A second, equally important, requirement is that they should respect the privacy of user data. While techniques exist to address each aspect in isolation, such as worst-case group optimization for the former and differentially private SGD for the latter, these are often at odds with with each other, and no practical method currently exists to enforce both requirements simultaneously. In this work, we overcome this problem and propose an algorithm for optimizing the worst-case group accuracy in a differentially private way. Our main contribution is ASC (Adaptively Sampled and Clipped Worst-case Group Optimization), which adaptively controls both the sampling rate and the clipping threshold of each group's gradient contributions. Thereby, it is able to reweight the training objective in favor of harder-to-learn groups, while keeping the noise required to enforce privacy low enough to preserve model utility. Our experiments show that ASC achieves substantially higher worst-case group accuracy than prior work, without sacrificing overall average accuracy.
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。