avatar

Chia-Yuan Wu

Lehigh ISE PhD student

About

I am a third-year Ph.D. student in the Department of Industrial and Systems Engineering (ISE) at Lehigh University under the supervision of Prof. Daniel P. Robinson. I received my M.S. from the Department of Industrial Engineering and Management in 2017, and my B.B.A. from the Department of Management Science in 2015 both at National Chiao Tung University in Hsinchu, Taiwan.

I currently conduct research in fair machine learning, fair federated learning, and synthetic data generation. My work focuses on mitigating unfairness, preserving privacy, and reducing communication costs through innovative methods like bilevel optimization and data distillation. Before joining Lehigh University, I worked as a system design engineer at Advanced Micro Devices, Inc. (AMD) and AU Optronics Corp. (AUO) in Hsinchu, Taiwan.

Education

  • Ph.D., Industrial and Systems Engineering, Lehigh University, Bethlehem, PA, USA, 2022–present
  • M.S., Industrial Engineering and Management, National Chiao Tung University, Hsinchu, Taiwan, 2015–2017
  • B.B.A., Management Science, National Chiao Tung University, Hsinchu, Taiwan, 2011–2015

Experience

  • Teaching Assistant, Lehigh University, Bethlehem, PA, USA, Aug. 2024–Dec. 2024
  • Graduate Assistant, Lehigh University, Bethlehem, PA, USA, Jul. 2024–Aug. 2024
  • Research Assistant, Lehigh University, Bethlehem, PA, USA, Jan. 2023–Jun. 2024
  • Software System Designer, Advanced Micro Devices, Inc. (AMD), Hsinchu, Taiwan, Apr. 2021–Jul. 2022
  • Senior Software Engineer, AU Optronics Corp. (AUO), Hsinchu, Taiwan, Sept. 2017–Apr. 2021
  • Intern, Taiwan Semiconductor Manufacturing Company (TSMC), Hsinchu, Taiwan, Jul. 2016–Aug. 2016

Publications

  • Using Synthetic Data to Mitigate Unfairness and Preserve Privacy through Single-Shot Federated Learning (Link)
    Chia-Yuan Wu, Frank E. Curtis, and Daniel P. Robinson
    Preprint in review, 2024

Conferences

  • MOPTA 2024, Bethlehem, PA, August 2024. (presentation)
    Enhancing Fairness in Machine Learning through Training Synthetic Datasets in Multi-Client Scenarios.
  • MOPTA 2023, Bethlehem, PA, August 2023. (attendance)