Virginia Polytechnic Institute & State University (Virginia Tech) was awarded a $165,200 project grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering program (CFDA 47.070) to support research titled "COLLABORATIVE RESEARCH: CNS CORE: SMALL: HIERARCHICAL FEDERATED LEARNING OVER WIRELESS EDGE NETWORKS: PERFORMANCE ANALYSIS AND OPTIMIZATION."
Under this three-year award beginning November 1, 2021, Virginia Tech researchers will analyze and optimize hierarchical federated learning techniques for wireless edge networks. Federated learning enables distributed training of machine learning models across decentralized edge devices while keeping private training data localized. The researchers aim to improve the performance of hierarchical federated learning approaches through analysis of communication overhead, statistical efficiency, and system scalability under realistic wireless network conditions. Insights from this work could help advance privacy-preserving distributed machine learning techniques applicable to emerging applications of edge artificial intelligence and the Internet of Things.