提出可控制高置信度公平性的表示学习框架，保障不同群体预测偏差不超设定阈值。
Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
- 通过优化对抗模型实现高置信度公平性保障
- 在三个真实数据集上验证，始终将不公平性控制在预设阈值内
- 适合关注算法公平性且需可量化保障的研究者与应用开发者
表示学习被广泛用于生成可在多个下游任务中泛化的表示。确保表示学习中的公平性至关重要，以避免在下游任务中对特定人口群体产生不公平。本文首次正式提出学习具有高置信度公平性的表示的任务，目标是保证每个下游预测中的群体差异不超过用户定义的误差阈值ε，且该保证具有可控制的高概率。为此，我们提出FRG（Fair Representation learning with high-confidence Guarantees）框架，通过优化对抗模型实现这一目标。我们在三个真实世界数据集上对FRG进行了实证评估，并与六种最先进的公平表示学习方法进行比较。结果表明，FRG在多种下游模型和任务中均能一致地限制不公平性。
原文摘要 · Abstract (English)
Representation learning is increasingly applied to generate representations that generalize well across multiple downstream tasks. Ensuring fairness guarantees in representation learning is crucial to prevent unfairness toward specific demographic groups in downstream tasks. In this work, we formally introduce the task of learning representations that achieve high-confidence fairness. We aim to guarantee that demographic disparity in every downstream prediction remains bounded by a *user-defined* error threshold $ε$, with *controllable* high probability. To this end, we propose the ***F**air **R**epresentation learning with high-confidence **G**uarantees (FRG)* framework, which provides these high-confidence fairness guarantees by leveraging an optimized adversarial model. We empirically evaluate FRG on three real-world datasets, comparing its performance to six state-of-the-art fair representation learning methods. Our results demonstrate that FRG consistently bounds unfairness across a range of downstream models and tasks.
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。