用梯度图识别不公平，无需人口信息也能提升模型公平性
Fairness without Demographics through Learning Graph of Gradients
- 构建梯度相似样本的图结构，通过对抗加权实现软分组
- 在无性别/种族数据下显著提升公平性，准确率损失小
- 对噪声鲁棒，适合隐私敏感场景下的公平性优化
机器学习系统常对特定人群产生偏差，导致算法不公平。由于隐私和数据质量问题，训练数据中可能缺失人口信息，且不同人口特征的复杂交互会生成大量未知少数子群体，限制了群体公平性的应用。现有无人口信息的公平性方法多依赖特征与群体的相关性，本文认为模型梯度同样具有价值。我们证明梯度与群体间的相关性可用于识别并改善群体公平性。通过对抗加权架构，构建样本间梯度相似性图，并从中学习样本权重。不同于从特征和标签聚类生成代理敏感属性的代理分组方法，本方法利用图结构作为软分组机制，对噪声更鲁棒。实验表明，该方法对噪声稳健，能显著提升公平性，且整体准确率下降有限。
原文摘要 · Abstract (English)
Machine learning systems are notoriously prone to biased predictions about certain demographic groups, leading to algorithmic fairness issues. Due to privacy concerns and data quality problems, some demographic information may not be available in the training data and the complex interaction of different demographics can lead to a lot of unknown minority subpopulations, which all limit the applicability of group fairness. Many existing works on fairness without demographics assume the correlation between groups and features. However, we argue that the model gradients are also valuable for fairness without demographics. In this paper, we show that the correlation between gradients and groups can help identify and improve group fairness. With an adversarial weighting architecture, we construct a graph where samples with similar gradients are connected and learn the weights of different samples from it. Unlike the surrogate grouping methods that cluster groups from features and labels as proxy sensitive attribute, our method leverages the graph structure as a soft grouping mechanism, which is much more robust to noises. The results show that our method is robust to noise and can improve fairness significantly without decreasing the overall accuracy too much.
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。