Taehwan Lee (이태환)

Research Interests

• Federated and Decentralized Learning

• Information and Communication Theory

Education

• Ph.D in Artificial Intelligence Graduate School, Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea.

  • • 1. • Advisor: Sung Whan Yoon (Lab: MIIT)

         • Mar. 2022 ~ Present

    • MS in Electrical Engineering at Ulsan National Institute of Science and Technology (UNIST), Ulsan, South Korea.

      1. • Advisor: Jinho Chung

         • Mar. 2017 ~ Aug. 2019

• B.S. in Electronic Engineering, Hanbat National University, Daejeon, South Korea.

  • • 1. • Advisor:   Kyoungjae Lee (Lab: WiSL)

         • Mar. 2011 ~ Feb. 2017.

Publications

*Equal contribution.

• Taehwan Lee*, Kyeongkook Seo*, Jaejun Yoo, Sung Whan Yoon, "Understanding Flatness in Generative Models: Its Role and Benefits," in International Conference on Computer Vision (ICCV), Honolulu, HI, 2025. [arXiv] [Project]

• SeungBum Ha*, Taehwan Lee*, Jiyoun Lim, Sung Whan Yoon, "Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation," Pattern Recognition Letters [arXiv] [GitHub]

• 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. [paper][GitHub]

• 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

• "Rethinking the Flat Minima Searching in Federated Learning" is awarded as the finalist of Qualcomm Innovation Fellowship Korea (QIFK) 2024 [Link].

• Teaching Assistant: Electrical Engineering Programming

  • Course: EE233, 2025 spring @ UNIST. 

  • Description: Basic programming tools for electrical engineering (C++).

• Teaching Assistant: Electrical Engineering Programming

  • Course: EE233, 2024 spring @ UNIST. 

  • Description: Basic programming tools for electrical engineering (C++).

Projects

• ETRI 위탁과제(다계층 연합학습 시뮬레이션 및 기여도 측정 도구 제작, Jun. 2024 - Nov. 2024)

  1. • Funded by ETRI

     • This research project is to develop a robust and flexible simulation environment for hierarchical and asynchronous federated learning algorithms.

     • My research is focused on coding the hierarchical and asynchronous structure of federated learning.

• 한국-미국(NSF) 국립과학재단 국제 공동 연구(Dec. 2021 - Nov. 2024) 

• Funded by IITP 

• My research part is focused on developing an algorithm that is robust to the heterogeneity of clients in federated learning.

• Academic results: "Rethinking the Flat Minima Searching in Federated Learning" in the 41st ICML.

• ETRI 위탁과제(다중 추론 성능 기반 연합학습 비동기 합의 실험 환경 구축, Jun. 2023 - Nov. 2023)

  1. • Funded by ETRI

     • This research project aims to develop a hierarchical and asynchronous federated learning algorithm.

• ETRI 위탁과제(자원 은닉형 딥러닝 모델 실현 가능성 검증 기술 개발, Apr. 2023 - Nov. 2023)

  1. • 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.