Disagreement-based Active Learning

Junghyun Lee
Oct 27, 2020 project

Project #1. Querying Easily Flip-flopped Samples for Deep Active Learning

Accepted to ICLR 2024. Joint work with Currently work in progress with Seong Jin Cho (KAIST EE), Gwangsu Kim (JBNU Statistics), Jinwoo Shin (KAIST AI), and Chang D. Yoo (KAIST AI).

Active Learning Statistics
Junghyun Lee
Junghyun Lee
PhD Student

PhD student at GSAI, KAIST, jointly advised by Prof. Se-Young Yun and Prof. Chulhee Yun. Interested in mathematical and theoretical AI, i.e., essentially any machine learning challenges necessitating mathematical analysis. Recently focused on statistical problems arising from RLHF, including interactive machine learning and low-dimensional structure recovery.

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