In-Processing Modeling Techniques for Machine Learning Fairness: A Survey
In-Processing Modeling Techniques for Machine Learning Fairness: A Survey
复制标题
DOI：
10.1145/3551390
复制
发表时间：
2022-07
影响因子：
3.6
通讯作者：
Mingyang Wan;D. Zha;Ninghao Liu;Na Zou
中科院分区：
文献类型：
--
作者：
Mingyang Wan;D. Zha;Ninghao Liu;Na Zou
机器学习模型在高风险应用中变得越来越普遍。尽管在性能方面有明显的好处，但这些模型可能会表现出对少数群体的歧视，并导致决策过程中的公平问题，从而对个人和社会造成严重的负面影响。近年来，已经开发了各种技术来减轻机器学习模型的不公平性。其中，处理中方法越来越受到社区的关注，在模型设计过程中直接考虑公平性，以引入本质公平的模型，从根本上缓解输出和表示的公平性问题。在本次调查中，我们回顾了处理中公平性缓解技术的当前进展。根据模型中实现公平性的位置，我们将其分为显式方法和隐式方法，前者直接将公平性指标纳入训练目标，后者侧重于细化潜在表示学习。最后，我们通过讨论该社区的研究挑战来结束调查，以激励未来的探索。
Machine learning models are becoming pervasive in high-stakes applications. Despite their clear benefits in terms of performance, the models could show discrimination against minority groups and result in fairness issues in a decision-making process, leading to severe negative impacts on the individuals and the society. In recent years, various techniques have been developed to mitigate the unfairness for machine learning models. Among them, in-processing methods have drawn increasing attention from the community, where fairness is directly taken into consideration during model design to induce intrinsically fair models and fundamentally mitigate fairness issues in outputs and representations. In this survey, we review the current progress of in-processing fairness mitigation techniques. Based on where the fairness is achieved in the model, we categorize them into explicit and implicit methods, where the former directly incorporates fairness metrics in training objectives, and the latter focuses on refining latent representation learning. Finally, we conclude the survey with a discussion of the research challenges in this community to motivate future exploration.