Abstract
No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “The present invention relates generally to federated learning , and more particularly to sketched and clustered federated learning with automa tic tuning. “Federated learning is a distributed learning framework that enables training a model from decentralized data located at client sites, without the data ever lea ving the client sites. Compared to a centralized model, in which training requir es all the data to be transmitted to and stored in a central location (e.g., a d ata center), federated learning has the benefits of preserving data privacy whil e avoiding transmission of large volumes.
NETL
NSTL