This paper studies long-term fair machine learning which aims to mitigate group disparity over the long term in sequential decision-making systems. To define long-term fairness, we leverage the temporal causal graph and use the 1-Wasserstein distance between the interventional distributions of different demographic groups at a sufficiently large time step as the quantitative metric. Then, we propose a three-phase learning framework where the decision model is trained on high-fidelity data generated by a deep generative model. We formulate the optimization problem as a performative risk minimization and adopt the repeated gradient descent algorithm for learning. The empirical evaluation shows the efficacy of the proposed method using both synthetic and semi-synthetic datasets.

翻译：本文研究长期公平机器学习，旨在减轻序贯决策系统中长期存在的群体差异。为定义长期公平性，我们利用时间因果图，并以足够大时间步长下不同人口群体干预分布之间的1-Wasserstein距离作为量化指标。随后，我们提出一个三阶段学习框架，决策模型基于深度生成模型生成的高保真数据进行训练。我们将优化问题形式化为执行风险最小化，并采用重复梯度下降算法进行学习。实证评估表明，所提方法在合成数据集和半合成数据集上均具有有效性。