Deploying machine learning (ML) models often requires both fairness and privacy guarantees. Both of these objectives present unique trade-offs with the utility (e.g., accuracy) of the model. However, the mutual interactions between fairness, privacy, and utility are less well-understood. As a result, often only one objective is optimized, while the others are tuned as hyper-parameters. Because they implicitly prioritize certain objectives, such designs bias the model in pernicious, undetectable ways. To address this, we adopt impartiality as a principle: design of ML pipelines should not favor one objective over another. We propose impartially-specified models, which provide us with accurate Pareto frontiers that show the inherent trade-offs between the objectives. Extending two canonical ML frameworks for privacy-preserving learning, we provide two methods (FairDP-SGD and FairPATE) to train impartially-specified models and recover the Pareto frontier. Through theoretical privacy analysis and a comprehensive empirical study, we provide an answer to the question of where fairness mitigation should be integrated within a privacy-aware ML pipeline.
翻译:部署机器学习模式往往需要公平和隐私的保障。这两个目标都与模型的效用(例如准确性)有着独特的权衡。但是,公平、隐私和效用之间的相互互动不太容易理解。结果,往往只有一个目标得到优化,而其他目标则被调整为超参数。由于它们暗含着某些目标的优先次序,这种设计将模型偏向于有害、无法检测的方式。为了解决这个问题,我们采用公正原则:设计ML管道不应偏向于另一个目标。我们提出了公正而明确的模型,为我们提供了表明目标之间内在权衡的准确的Pareto边界。延长了两个维护隐私的可理解的ML框架,我们提供了两种方法(FairDP-SGD和FairPATE)来培训公正指定的模型和恢复Pareto边界。通过理论隐私权分析和全面的经验研究,我们提出了在什么情况下应当将公平缓解纳入隐私意识ML管道的问题。