Core Concepts
Over-the-Air Federated Learning algorithm aims to provide fairness and robustness through minmax optimization.
Stats
Over-the-Air Computation is more efficient as the number of agents grows.
FedFAir algorithm achieves around 90% accuracy after approximately 5000 iterations.
FedAVG algorithm achieves approximately 70-75% accuracy after 100000 iterations.
Quotes
"Over-the-Air Computation is more efficient as the number of agents grows."
"FedFAir algorithm achieves around 90% accuracy after approximately 5000 iterations."
"FedAVG algorithm achieves approximately 70-75% accuracy after 100000 iterations."