We conduct an exploratory study that looks at incorporating John Rawls' ideas on fairness into existing unsupervised machine learning algorithms. Our focus is on the task of clustering, specifically the k-means clustering algorithm. To the best of our knowledge, this is the first work that uses Rawlsian ideas in clustering. Towards this, we attempt to develop a postprocessing technique i.e., one that operates on the cluster assignment generated by the standard k-means clustering algorithm. Our technique perturbs this assignment over a number of iterations to make it fairer according to Rawls' difference principle while minimally affecting the overall utility. As the first step, we consider two simple perturbation operators -- $\mathbf{R_1}$ and $\mathbf{R_2}$ -- that reassign examples in a given cluster assignment to new clusters; $\mathbf{R_1}$ assigning a single example to a new cluster, and $\mathbf{R_2}$ a pair of examples to new clusters. Our experiments on a sample of the Adult dataset demonstrate that both operators make meaningful perturbations in the cluster assignment towards incorporating Rawls' difference principle, with $\mathbf{R_2}$ being more efficient than $\mathbf{R_1}$ in terms of the number of iterations. However, we observe that there is still a need to design operators that make significantly better perturbations. Nevertheless, both operators provide good baselines for designing and comparing any future operator, and we hope our findings would aid future work in this direction.
Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);Institute of High-Performance Computing, Agency for Science, Technology and Research(新加坡科技研究局高性能计算研究所);Centre for Frontier AI Research, Agency for Science, Technology and Research(新加坡科技研究局前沿人工智能研究中心);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies
RMIT University(皇家墨尔本理工大学);University of Michigan(密歇根大学);ETH Zurich(苏黎世联邦理工学院);UNSW Sydney(新南威尔士大学悉尼分校);ARC Centre of Excellence for Automated Decision-Making and Society(自动化决策与社会卓越研究中心);School of Computing Technologies, RMIT University(皇家墨尔本理工大学计算技术学院);Department of Mathematics, University of Michigan(密歇根大学数学系);Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系);School of Computer Science and Engineering, UNSW Sydney(新南威尔士大学悉尼分校计算机科学与工程学院)
Exploring the Unfairness of DP-SGD Across Settings
University of Copenhagen(哥本哈根大学)
最终用户和监管机构需要私有和公平的人工智能模型,但之前的研究表明,这些目标可能不一致。我们使用CivilComments来评估将{ \em de facto}标准隐私方法DP-SGD应用于多个公平性指标的影响。我们评估了DP-SGD的三种实现:降维(PCA),线性分类(逻辑回归)和鲁棒深度学习(Group-DRO)。在线性分类和鲁棒深度学习的情况下,我们在隐私和公平性之间建立了负对数相关。DP-SGD对PCA的公平性没有显著影响,但经检查,似乎也没有导致私人陈述。
Exploring Bias and Prediction Metrics to Characterise the Fairness of Machine Learning for Equity-Centered Public Health Decision-Making: A Narrative Review
Vector Institute for Artificial Intelligence(人工智能向量研究院);University of Tennessee(田纳西大学);York University(约克大学);McGill University(麦吉尔大学)
Price of Fairness in Bandits: A Tight Minimax Characterization
Indian Institute of Technology Kharagpur(印度理工学院卡拉格浦尔分校);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Indian Institute of Technology Kanpur(印度理工学院坎浦尔分校)