Dr. Hongchang Gao, an assistant professor in the Department of Computer and Information Sciences, has received the prestigious NSF CAREER award for his research in federated learning. This five-year award, titled "Decentralized Federated Compositional Learning: Algorithm and Theory," recognizes Dr. Gao’s innovative contributions to advancing this field.
Federated learning (FL) is a transformative collaborative learning framework that enables training machine learning models on large-scale distributed data without sharing raw data, making it invaluable for numerous real-world applications. However, existing federated learning frameworks primarily focus on traditional machine learning models and do not address emerging learning paradigms. Additionally, they restrict their focus to centralized communication strategies, which are susceptible to single-point failures.
Dr. Gao’s project seeks to address these limitations by developing a new decentralized federated compositional learning framework. This framework aims to support FL for emerging compositional learning paradigms, systematically addressing both computational and communication challenges. The project involves creating novel algorithms tailored to these challenges and providing rigorous theoretical guarantees. The proposed framework will be evaluated on real-world tasks, including biomedical applications and general machine learning scenarios, showcasing its versatility and effectiveness.
Dr. Gao’s work also emphasizes integrating cutting-edge research with education, providing valuable opportunities for students from diverse backgrounds to engage in this rapidly evolving field.
In addition to the NSF CAREER award, Dr. Gao has also received a new NSF award for a collaborative project focused on trustworthy decentralized federated learning.
Congratulations to Dr. Gao for these outstanding achievements and his contributions to advancing the field of federated learning!