In over-the-air federated learning, increasing the number of participating clients simultaneously reduces information leakage, induces channel hardening that removes fading distortions, and improves the convergence rate.
On analog gradient descent learning over multiple access fading channels,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Federated Learning Over the Air: The Blessing of Scaling Up
In over-the-air federated learning, increasing the number of participating clients simultaneously reduces information leakage, induces channel hardening that removes fading distortions, and improves the convergence rate.