Yiyu Lydia Chen

Yiyu Lydia Chen is a Professor in the Department of Computer Science at the University of Neuchatel in Switzerland and Delft University of Technology in the Netherlands. She serves as the director of the Distributed Learning Systems Lab and holds a dual academic appointment across these institutions. Her research spans distributed machine learning systems, generative AI, and dependability and privacy enhancing technologies.

Chen earned her PhD from Pennsylvania State University and completed her BA at National Taiwan University. Prior to her academic career, she spent over a decade (2007-2018) as a research staff member at IBM Research Zurich Lab, bringing valuable industry experience to her academic work.

Her research focuses on developing machine learning and stochastic models with applications in data centers, edge systems, and semiconductor and material science. Current research directions include generative AI systems for discovering unknown patterns through large language models and diffusion models, and trustworthy learning systems designed to be robust against adversarial manipulation of data inputs. Her work bridges theoretical foundations with practical applications in natural science and manufacturing domains.

Chen's extensive publication record shows a clear trajectory toward privacy-preserving federated learning, tabular data synthesis, and security mechanisms for generative models. Recent work demonstrates increasing focus on watermarking techniques for diffusion models, gradient inversion attacks, and privacy-preserving vertical federated learning frameworks.

Her research is supported by major funding bodies including the Swiss National Science Foundation, Dutch National Science Foundation, European Union, IBM Research, ABB, ASM, Tata Steel, and ASML through projects such as DepMat (2023-27), Dapprox (2017-2021), Women in Big Data (2018-2022), GENiC (2013-2015), and LoadOpt (2011-2015).

Chen actively mentors the next generation of researchers, supervising numerous PhD students including Jeroen Galjaard, Chaoyi Zhu, and Aditya Shankar, while also guiding Master's and Bachelor's students through thesis projects focused on cutting-edge topics in machine learning and distributed systems.

As director of the Distributed Learning Systems Lab, she leads a vibrant research group tackling fundamental challenges in distributed machine learning, with recent breakthroughs in federated learning security, tabular data generation, and efficient model training on edge devices. Her team regularly publishes at top-tier venues including ICML, ICLR, IEEE DSN, and ACM conferences.