Project Grant 2339545

This $196,548 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support Temple University's research to develop a new Decentralized Federated Compositional Learning (DFCL) framework. The objective is to enable federated learning, an emerging collaborative machine learning paradigm, for the compositional learning paradigm. The project aims to address key computational and communication challenges in decentralized federated learning, with applications in healthcare, social science, and other domains. The award will fund the research over a 5-year period from September 2024 to August 2029. No sub-awards are planned under this grant.