Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation learning and then discard the latent code dimensions correlated with sensitive attributes (e.g., gender). Nevertheless, these approaches may suffer from incomplete disentanglement and overlook proxy attributes (proxies for sensitive attributes) when processing real-world data, especially for unstructured data, causing performance degradation in fairness and loss of useful information for downstream tasks. In this paper, we propose a novel fairness framework that performs debiasing with regard to both sensitive attributes and proxy attributes, which boosts the prediction performance of downstream task models without complete disentanglement. The main idea is to, first, leverage gradient-based explanation to find two model focuses, 1) one focus for predicting sensitive attributes and 2) the other focus for predicting downstream task labels, and second, use them to perturb the latent code that guides the training of downstream task models towards fairness and utility goals. We show empirically that our framework works with both disentangled and non-disentangled representation learning methods and achieves better fairness-accuracy trade-off on unstructured and structured datasets than previous state-of-the-art approaches.

翻译：机器学习系统在某些人口群体上会产生有偏结果，这被称为公平性问题。近期解决该问题的方法通过解耦表示学习学习潜在编码（即表示），然后丢弃与敏感属性（如性别）相关的潜在编码维度。然而，这些方法在处理真实数据（尤其是非结构化数据）时可能面临解耦不完整的问题，并忽略代理属性（敏感属性的代理变量），导致公平性性能下降以及下游任务有用信息损失。本文提出一种新型公平性框架，同时对敏感属性和代理属性进行去偏处理，无需完全解耦即可提升下游任务模型的预测性能。核心思想是：首先，利用基于梯度的解释找到两种模型关注点——1）预测敏感属性的关注点，2）预测下游任务标签的关注点；其次，利用这两种关注点扰动潜在编码，引导下游任务模型训练向公平性和效用目标优化。实验表明，我们的框架适用于解耦和非解耦表示学习方法，在非结构化和结构化数据集上均能实现比现有最优方法更优的公平性-准确性权衡。