揭示图像分析中导致模型不公平的因果与统计偏见问题。
A Primer on Causal and Statistical Dataset Biases for Fair and Robust Image Analysis
- 提出'不公午餐'和'子组可分性'两类被忽视的偏见机制
- 指出当前公平表征学习方法无法有效解决上述问题
- 为构建更公平鲁棒的视觉模型指明新方向，适合关注公平性的研究者
机器学习模型在真实场景中常出现失败，尤其在医疗诊断等高风险领域，其失败可能引发严重社会影响。本文系统梳理了图像分析中导致模型失效的因果与统计偏见结构，揭示两类此前被忽视的关键问题：'不公午餐'（no fair lunch）问题与'子组可分性'（subgroup separability）问题。我们分析了现有公平表征学习方法为何未能有效应对这些问题，并提出了未来研究的潜在路径，旨在推动更公平、更鲁棒的视觉分析技术发展。
原文摘要 · Abstract (English)
Machine learning methods often fail when deployed in the real world. Worse still, they fail in high-stakes situations and across socially sensitive lines. These issues have a chilling effect on the adoption of machine learning methods in settings such as medical diagnosis, where they are arguably best-placed to provide benefits if safely deployed. In this primer, we introduce the causal and statistical structures which induce failure in machine learning methods for image analysis. We highlight two previously overlooked problems, which we call the \textit{no fair lunch} problem and the \textit{subgroup separability} problem. We elucidate why today's fair representation learning methods fail to adequately solve them and propose potential paths forward for the field.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。