Active Learning from Oracle with Knowledge Blind Spot

Active learning traditionally assumes that an oracle is capable of providing labeling information for each query instance. This paper formulates a new research problem which allows an oracle admit that he/she is incapable of labeling some query instances or simply answer “I don’t know the label”. We define a unified objective function to ensure that each query instance submitted to the oracle is the one mostly needed for labeling and the oracle should also has the knowledge to label. Experiments based on different types of knowledge blind spot (KBS) models demonstrate the effectiveness of the proposed design.

Authors

• Meng Fang University of Liverpool
• Xingquan Zhu Florida Atlantic University
• Chengqi Zhang Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University

Keywords

No keywords are indexed for this paper.