Real: A representative error-driven approach for active learning

• Main Authors: CHEN, Cheng, WANG, Yong, LIAO, Lizi, CHEN, Yueguo, DU, Xiaoyong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Active Learning; Error density; Error-driven; Informativeness; Labelings; Model training; Neighbourhood; Pseudo errors; Text classification; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8586; https://ink.library.smu.edu.sg/context/sis_research/article/9589/viewcontent/real.pdf
• Institution: Singapore Management University

Given a limited labeling budget, active learning (al) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training. To achieve this, al typically measures the informativeness of unlabeled instances based on uncertainty and diversity. However, i...