Description:
Reference #: 01573
The University of South Carolina is offering licensing opportunities for Methods for Multi-cell Over-the-Air Computation for Distributed Learning
Background:
Federated edge learning (FEEL) is a distributed learning framework that leverages the computational powers of edge devices (EDs) and uses the local data at the EDs without compromising their privacy to train a model. However, the communication aspect of FEEL stands as one of the main bottlenecks.
Invention Description:
This invention addresses the communication latency problem of training an artificial intelligence model together with the scalability issue of a single-cell wireless network. It reduces the latency with over-the-air computation and deploys a multi-cell network.
Potential Applications:
The technology could be useful for artificial intelligence technologies over wireless or sensor networks, 5G and beyond, 6G wireless standardization, IEEE 802.11 Wi-Fi.
Advantages and Benefits:
This scheme does not need a channel inversion at EDs and ESs. From this aspect, it is compatible with time-varying channels and does not lose the gradient information due to the truncation. It also does not require CSIs at both EDs and ESs or multiple antennas for over-the-air computation. Moreover, in our user-centric approach with heterogeneous data distribution, EDs can learn to classify labels of their data without availability of some digits on their datasets.