无需敏感属性信息即可有效降低模型偏见。
Unbiased Model Prediction Without Using Protected Attribute Information
- 利用非敏感属性的辅助信息实现去偏
- 在LFWA和CelebA上显著减少性别年龄组偏见
- 适合隐私敏感或无法获取敏感属性的场景
偏差问题在深度学习领域持续存在，模型对不同人口统计子群体的表现差异明显。尽管已有多种算法提升模型公平性，但多数依赖敏感属性信息，严重限制了实际应用。为此，本文提出一种新算法——非敏感属性去偏（NPAD），无需使用敏感属性即可实现去偏。该算法利用非敏感属性提供的辅助信息优化模型，并设计了两种损失函数：通过属性聚类去偏损失（DACL）和过滤冗余损失（FRL）以实现公平性目标。在LFWA和CelebA数据集上进行的人脸属性预测实验表明，该方法在不同性别和年龄子群体间显著降低了偏见。
原文摘要 · Abstract (English)
The problem of bias persists in the deep learning community as models continue to provide disparate performance across different demographic subgroups. Therefore, several algorithms have been proposed to improve the fairness of deep models. However, a majority of these algorithms utilize the protected attribute information for bias mitigation, which severely limits their application in real-world scenarios. To address this concern, we have proposed a novel algorithm, termed as \textbf{Non-Protected Attribute-based Debiasing (NPAD)} algorithm for bias mitigation, that does not require the protected attribute information. The proposed NPAD algorithm utilizes the auxiliary information provided by the non-protected attributes to optimize the model for bias mitigation. Further, two different loss functions, \textbf{Debiasing via Attribute Cluster Loss (DACL)} and \textbf{Filter Redundancy Loss (FRL)} have been proposed to optimize the model for fairness goals. Multiple experiments are performed on the LFWA and CelebA datasets for facial attribute prediction, and a significant reduction in bias across different gender and age subgroups is observed.
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。