[论文解读] The Pursuit of Fairness in Artificial Intelligence Models: A Survey

Tahsin Alamgir Kheya, Mohamed Reda Bouadjenek+1 more|arXiv (Cornell University)|Mar 26, 2024

Ethics and Social Impacts of AI被引用 6

一句话总结

本次2024年综述评估AI中的公平性定义、偏见类型及减缓方法，评估它们在各领域的适用性及伦理影响。

ABSTRACT

Artificial Intelligence (AI) models are now being utilized in all facets of our lives such as healthcare, education and employment. Since they are used in numerous sensitive environments and make decisions that can be life altering, potential biased outcomes are a pressing matter. Developers should ensure that such models don't manifest any unexpected discriminatory practices like partiality for certain genders, ethnicities or disabled people. With the ubiquitous dissemination of AI systems, researchers and practitioners are becoming more aware of unfair models and are bound to mitigate bias in them. Significant research has been conducted in addressing such issues to ensure models don't intentionally or unintentionally perpetuate bias. This survey offers a synopsis of the different ways researchers have promoted fairness in AI systems. We explore the different definitions of fairness existing in the current literature. We create a comprehensive taxonomy by categorizing different types of bias and investigate cases of biased AI in different application domains. A thorough study is conducted of the approaches and techniques employed by researchers to mitigate bias in AI models. Moreover, we also delve into the impact of biased models on user experience and the ethical considerations to contemplate when developing and deploying such models. We hope this survey helps researchers and practitioners understand the intricate details of fairness and bias in AI systems. By sharing this thorough survey, we aim to promote additional discourse in the domain of equitable and responsible AI.

研究动机与目标

• 在医疗、教育、金融等高风险决策领域，推动AI公平性的必要性。
• 整理现有的公平性定义并建立对ML系统中偏见的全面分类法。
• 研究数据、人工和模型来源的偏见成因，并调研减缓技术及其在各领域的适用性。
• 讨论偏见AI对用户体验的影响以及开发与部署中的伦理考量。
• 识别当前公平性文献中的挑战与局限，以指导未来研究。

提出的方法

• 对ML中的公平性定义和偏见进行文献综合。
• 提出并阐明ML中的公平性分类法（群体、个人、交叉性、因果基）并举例。
• 按数据驱动、人工和模型维度对偏见进行分类并给出示例。
• 调查减缓策略及其在医疗、教育、金融和NLP等领域的适用性。
• 与现有综述进行对比，凸显被忽视的议题，如用户体验影响和伦理。
• 对当前公平性研究中的挑战与局限性进行批判性讨论。

实验结果

研究问题

• RQ1 在机器学习中使用的主要公平性定义和分类有哪些？
• RQ2 ML流程中出现了哪些类型的偏见？如何减缓？
• RQ3 不同应用领域中公平性概念和偏见如何体现？
• RQ4 部署公平AI系统时的伦理考量及对用户体验的影响是什么？

主要发现

• ML中的公平性是多方面的，存在众多定义，在现有标准下实现绝对公平并非可行。
• 全面的分类法区分群体公平性、个体公平性、交叉性公平性和因果基等概念，以及各种指标（如 Demographic Parity、Equalized Odds、Calibration）。
• 偏见发生在数据、人工和模型层面，涵盖测量、表示、标注、采样、历史和部署等偏见，以及其他类型。
• 公平相关文献数量持续增长，既有综述覆盖广泛或领域特定的方面；本工作强调将用户体验和伦理作为尚未充分研究的领域。
• 本文讨论伦理准则以及在部署AI系统时考虑社会技术背景以维持信任的必要性。