用新方法让模型在公平与性能间更好平衡。
Deep Fair Learning: A Unified Framework for Fine-tuning Representations with Sufficient Networks
- 通过微调时引入惩罚项，强制敏感属性与表征条件独立。
- 在多种数据结构上均优于现有最优方法。
- 支持连续、离散、多组等各类敏感属性。
确保机器学习中的公平性是一项关键且具有挑战性的任务，因为有偏的数据表示常导致不公平的预测。为此，我们提出 Deep Fair Learning，一个将非线性充分维度缩减与深度学习相结合的框架，用于构建公平且信息丰富的表示。通过在微调过程中引入一种新型惩罚项，该方法在源头上消除偏差，同时保持预测性能。与以往方法不同，该框架支持多种类型的敏感属性，包括连续型、离散型、二值型或多组类型。在多种数据结构上的实验表明，该方法在公平性与效用之间实现了更优平衡，显著优于当前最先进的基线方法。
原文摘要 · Abstract (English)
Ensuring fairness in machine learning is a critical and challenging task, as biased data representations often lead to unfair predictions. To address this, we propose Deep Fair Learning, a framework that integrates nonlinear sufficient dimension reduction with deep learning to construct fair and informative representations. By introducing a novel penalty term during fine-tuning, our method enforces conditional independence between sensitive attributes and learned representations, addressing bias at its source while preserving predictive performance. Unlike prior methods, it supports diverse sensitive attributes, including continuous, discrete, binary, or multi-group types. Experiments on various types of data structure show that our approach achieves a superior balance between fairness and utility, significantly outperforming state-of-the-art baselines.
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。