We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are useful for reconstruction and prediction, but are also \emph{flexibly fair}, meaning they can be easily modified at test time to achieve subgroup demographic parity with respect to multiple sensitive attributes and their conjunctions. We show empirically that the resulting encoder---which does not require the sensitive attributes for inference---enables the adaptation of a single representation to a variety of fair classification tasks with new target labels and subgroup definitions.
Model Debiasing via Gradient-based Explanation on Representation
City University of Hong Kong(香港城市大学);Hong Kong Research Center, Huawei(华为香港研究中心);NVIDIA Research(英伟达研究院);The Hong Kong University of Science and Technology(香港科技大学)
Unsupervised Model Selection for Variational Disentangled Representation Learning
DeepMind(深度思维)
最近已经证明,在简单的监督和强化学习任务中,解纠缠表示可以提高公平性、数据效率和泛化能力。为了将解纠缠表示的好处扩展到更复杂的领域和实际应用,重要的是要启用现有无监督方法的超参数调整和模型选择,而无需访问大多数数据集不可用的地面真值属性标签。本文针对这个问题,介绍了一个简单而强大的和可靠的方法,无监督的解纠缠模型选择。我们的方法,无监督解纠缠排名(UDR),利用最近的理论结果解释了为什么变分自编码器解纠缠(Rolinek et al,2019),通过在训练的模型表示之间进行成对比较来量化解纠缠的质量。我们表明,我们的方法对来自六个最先进的无监督分解表示学习模型类的5,400个模型中的现有监督替代方案进行了验证。此外,我们表明,我们的方法产生的排名以及相关的最终任务的性能在两个不同的域。
Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校)
Disentangled Representations from Non-Disentangled Models
Yandex(Yandex公司);Skolkovo Institute of Science and Technology (Skoltech)(斯科尔科沃科学技术研究院(Skoltech));National Research University Higher School of Economics(国立研究型大学高等经济学院)
On Disentangled Representations Learned From Correlated Data
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University of Toronto(多伦多大学);Vector Institute(向量研究所);Helmholtz AI(亥姆霍兹人工智能中心);Amazon(亚马逊);ETH Zurich(苏黎世联邦理工学院);Technical University of Denmark(丹麦技术大学);Mila(米拉研究所);Université de Montréal(蒙特利尔大学)
DISCO: A Hierarchical Disentangled Cognitive Diagnosis Framework for Interpretable Job Recommendation
School of Artificial Intelligence, Anhui University(安徽大学人工智能学院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Science and Technology of China(中国科学技术大学);Institutes of Physical Science and Information Technology, Anhui University(安徽大学物理与信息技术研究院);School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心)