We study the problem of fair classification within the versatile framework of Dwork et al. [ITCS '12], which assumes the existence of a metric that measures similarity between pairs of individuals. Unlike earlier work, we do not assume that the entire metric is known to the learning algorithm; instead, the learner can query this arbitrary metric a bounded number of times. We propose a new notion of fairness called metric multifairness and show how to achieve this notion in our setting. Metric multifairness is parameterized by a similarity metric $d$ on pairs of individuals to classify and a rich collection ${\cal C}$ of (possibly overlapping) "comparison sets" over pairs of individuals. At a high level, metric multifairness guarantees that similar subpopulations are treated similarly, as long as these subpopulations are identified within the class ${\cal C}$.
Partial Fairness Awareness: Belief-Guided Strategic Mechanism for Strategic Agents
National University of Defense Technology, Changsha, China（国防科技大学）；Peking University, Beijing, China（北京大学）；Shanghai University of Finance and Economics, Shanghai, China（上海财经大学）；ZGC Laboratory, Beijing, China（ZGC实验室）；Faculty of Computing, Harbin Institute of Technology, Harbin, China（哈尔滨工业大学计算机学院）
Affirmative Algorithms: The Legal Grounds for Fairness as Awareness
Stanford University（斯坦福大学）；Stanford Institute for Economic Policy Research（斯坦福经济政策研究所）；Stanford Institute for Human-Centered Artificial Intelligence（斯坦福以人为本人工智能研究所）；Partnership on AI（人工智能伙伴关系）
Accurate Fairness: Improving Individual Fairness without Trading Accuracy
State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所计算机科学国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairness
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Tübingen AI Center（图宾根人工智能中心）；Mila Québec AI Institute（魁北克人工智能研究所）；McGill University（麦吉尔大学）
