Least Disagreement-based Active Learning

Junghyun Lee
Oct 27, 2020 project

TBD

  • Under review
  • Joint work with Seong Jin Cho (KAIST EE), Gwangsu Kim (JBNU Statistics), and Hee Suk Yoon, Joshua Tian Jin Tee & Chang D. Yoo (KAIST EE).

Querying Easily Flip-flopped Samples for Deep Active Learning

  • Accepted to ICLR 2024.
  • Joint work with Seong Jin Cho (KAIST EE), Gwangsu Kim (JBNU Statistics), Jinwoo Shin (KAIST AI), and Chang D. Yoo (KAIST EE).
Active Learning Statistics
Junghyun Lee
Junghyun Lee
PhD Student

PhD student at GSAI, KAIST, jointly advised by Profs. Se-Young Yun and Chulhee Yun. Research focuses on interactive machine learning, particularly at the intersection of RLHF and preference learning, and statistical analyses of large networks, with an emphasis on community detection. Broadly interested in mathematical and theoretical AI and related problems in mathematics.

Publications

Querying Easily Flip-flopped Samples for Deep Active Learning
Proposes a new active learning approach by proposing a new uncertainty measure called the least disagree metric, as well as its efficient estimator, which is proven to be asymptotically consistent. This is then combined with seeding to become a new active learning algorith, LDM-S, which is shown to outperform existing approaches across various architectures and datasets.
Seong Jin Cho, Gwangsu Kim, Junghyun Lee, Jinwoo Shin, Chang D. Yoo
PDF Cite Project
Querying Easily Flip-flopped Samples for Deep Active Learning