Taehwan Lee (이태환)
Ph.D Student
E-mail: taehwan@unist.ac.kr
Brief Bio: I have been a Ph.D. student affiliated with the Artificial Intelligence Graduate School (AIGS) at UNIST since March 2022. I obtained an MS (2019) degree from the Department of Electronic and Electrical Engineering at UNIST and a BS (2017) from the Department of Electronic Engineering at HBNU.
Research Interests
Federated and decentralized learning
Information & Communication Theory
Education
Ph.D in Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea.
Advisor: Sung Whan Yoon (Lab: MIIL)
Mar. 2022 ~ Present
MS in Electrical Engineering at Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea.
Advisor: Jinho Chung
Mar. 2017 ~ Aug. 2019
B.S. in Electronic Engineering, Hanbat National University, Daejeon, South Korea.
Advisor: Kyoungjae Lee (Lab: WiSL)
Mar. 2011 ~ Feb. 2017.
Publications
Taehwan. Lee, Sung Whan Yoon, "Rethinking the Flat Minima Searching in Federated Learning," in the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024.
Taehwan. Lee, Hee-Heon Jung, and Jin-Ho Chung. "A new one-coincidence frequency-hopping sequence set of length p2-p." 2018 IEEE Information Theory Workshop (ITW). IEEE, 2018.
Experiences
Teaching Assistant: Electrical Engineering Programming
Course: EE233, 2024 spring @ UNIST.
Description: Basic programming tools for electrical engineering (C++).
Projects
ETRI 위탁과제(다중 추론 성능 기반 연합학습 비동기 합의 실험 환경 구축, Jun. 2023 - Nov. 2023)
Funded by ETRI
This research project aims to develop a hierarchical and asynchronous federated learning algorithm.
My research is focused on coding the hierarchical structure of federated learning and analyzing the effect of asynchrony in federated learning.
ETRI 위탁과제(자원 은닉형 딥러닝 모델 실현 가능성 검증 기술 개발, Apr. 2023 - Nov. 2023)
Funded by ETRI
This research project aims to develop double-blind federated learning algorithms that secure both models and data.
My research is focused on adopting federated learning to Scene Graph Generation (SGG) tasks and constructing and analyzing the heterogeneity of the semantic dataset of Panoptic Scene Graph Generation (PSG) tasks.