Federated Learning in The Age of Foundation Models

About this Topic:

In the ever-evolving landscape of artificial intelligence, handling and leveraging data effectively has been and will continue to be a critical challenge, especially in the age of foundation models. Recent development in utilizing them, e.g. large language models (LLMs), has opened new horizons in the research. Although most algorithms are trained in a centralized fashion, access to necessary data can be restricted due to various factors such as privacy, regulation, geopolitics, and the sheer effort to move the datasets. Given the fundamentals of federated learning (FL) addressing the pivotal balance between data access and the collaborative enhancement of AI models, in this talk, the presenter will explore how FL can address the challenges with easy and scalable integration capabilities. Enabled by practical frameworks like NVIDIA FLARE, he will discuss the special challenges and solutions for embedding FL in foundation model development and customizations to enhance their accuracy and robustness. Ultimately, this talk underscores the transformative potential of FL in foundation models, offering insights into its current achievements and future possibilities.

About the Presenter:

Ziyue Xu (Senior, IEEE) received the B.S. from Tsinghua University in 2006, and M.S. & Ph.D. degrees from the University of Iowa in 2009 and 2012 respectively.

He is currently a Senior Scientist at NVIDIA, before which he was a Staff Scientist and Lab Manager at National Institutes of Health, New York, New York, USA. His research interests lie in the area of image analysis and computer vision with applications in biomedical imaging. He has been working on medical AI over the years along with fellow researchers and clinicians for clinical applications.

Dr. Xu is an IEEE Senior Member, Area Chair for major conferences, and Associate Editor for several journals including IEEE Transactions of Medical Imaging, and International Journal of Computer Vision.