We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention responses, and analyze its statistical consistency and query complexity under fairly natural assumptions on the noise and abstention rate of the labeler. This algorithm is adaptive in a sense that it can automatically request less queries with a more informed or less noisy labeler. We couple our algorithm with lower bounds to show that under some technical conditions, it achieves nearly optimal query complexity.
Active Learning with Imperfect Labels: Optimal Labeler Assignment and Sample Selection
School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta, GA 30332, USA（工业与系统工程学院 佐治亚理工学院 阿拉巴马州亚特兰大 30332, 美国）；Ford Motor Company（福特汽车公司）
Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards
The University of Michigan-Shanghai Jiao Tong University Joint Institute (UM-SJTU JI)（密歇根大学-上海交通大学联合学院）；Duke Kunshan University（昆山杜克大学）；NetEase Fuxi AI Lab（网易伏羲人工智能实验室）
Bayesian Active Learning With Abstention Feedbacks
Amazon Web Services（亚马逊云科技）；Dalhousie University（达尔豪斯大学）；Alibaba Inc.（阿里巴巴集团）；University of Delaware（特拉华大学）；AISIA Research Lab（AISIA研究实验室）；University of Science（理学院）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）
Addressing practical challenges in Active Learning via a hybrid query strategy
Kansas State University（堪萨斯州立大学）；Indian Institute of Technology Gandhinagar（甘地纳格尔印度理工学院）；Viking Analytics（维京分析公司）；Luleå University of Technology（吕勒奥理工大学）；Indian Institute of Technology Madras（马德拉斯印度理工学院）
Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies
Department of Computer Science, Aalto University（阿尔托大学计算机科学系）；Department of Computer Science, University of Helsinki（赫尔辛基大学计算机科学系）；ELLIS Institute Finland（芬兰埃利斯研究所）；Department of Computer Science, Manchester University（曼彻斯特大学计算机科学系）
