Training fair machine learning models, aiming for their interpretability and solving the problem of domain shift has gained a lot of interest in the last years. There is a vast amount of work addressing these topics, mostly in separation. In this work we show that they can be seen as a common framework of learning invariant representations. The representations should allow to predict the target while at the same time being invariant to sensitive attributes which split the dataset into subgroups. Our approach is based on the simple observation that it is impossible for any learning algorithm to differentiate samples if they have the same feature representation. This is formulated as an additional loss (regularizer) enforcing a common feature representation across subgroups. We apply it to learn fair models and interpret the influence of the sensitive attribute. Furthermore it can be used for domain adaptation, transferring knowledge and learning effectively from very few examples. In all applications it is essential not only to learn to predict the target, but also to learn what to ignore.
De-biased Representation Learning for Fairness with Unreliable Labels
Data Science Institute(数据科学研究所);University of Technology Sydney(悉尼科技大学);Tsinghua University(清华大学)
在保持所有任务相关信息的同时消除偏差对于公平表示学习方法来说是具有挑战性的,因为它们会产生随机或退化的表示。标签,当敏感属性与标签相关时。现有的工作建议注入的标签信息的学习过程中,以克服这些问题。然而,观察到的标签是干净的这一假设并不总是得到满足。事实上,标签偏见被认为是导致歧视的主要来源。换句话说,公平预处理方法在学习过程或评估阶段忽略了标签中编码的区分。这种矛盾给学习表征的公平性打上了一个问号。为了规避这个问题,我们探讨了以下问题:\emph{Can we learn fair representations predictable to latent ideal fair labels given only access to unreliable labels?}在这项工作中,我们提出了一个\textbf{D}电子- \textbf{B}基于\textbf{R} epresentation学习\textbf{F}空气(DBRF)框架,解开的敏感信息从非敏感属性,同时保持学习表示偏向理想的公平标签,而不是观察到的可预测的。我们通过信息论的概念,如互信息和信息瓶颈,制定了去偏学习框架。其核心理念是,DBRF主张在敏感信息有利于不可靠标签预测的情况下,不使用不可靠标签进行监管。在合成数据和真实数据上的实验结果表明,DBRF有效地学习了理想标签的去偏表示。
A New Perspective to Boost Performance Fairness for Medical Federated Learning
Australian National University(澳大利亚国立大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Guangxi Medical University(广西医科大学);Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局高性能计算研究所);Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(穆罕默德·本·扎耶德人工智能大学);The Hong Kong University of Science and Technology(香港科技大学)
Deconfounding age effects with fair representation learning when assessing dementia
Winterlight Labs;University of Toronto(多伦多大学);Li Ka Shing Knowledge Institute, St Michael’s Hospital(圣迈克尔医院李嘉诚知识研究所);Vector Institute for Artificial Intelligence(Vector人工智能研究所);Surgical Safety Technologies Inc(Surgical Safety Technologies公司)
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Cambridge(剑桥大学);Max Planck ETH Center for Learning Systems(马克斯·普朗克-苏黎世联邦理工学院学习系统中心);University of California, Berkeley(加利福尼亚大学伯克利分校)