An age-of-information Markov scheduling policy that balances client selection intervals is claimed to speed up federated learning convergence by 7.5-20% over random selection.
Real-time status: how often should one update?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Balancing Client Participation in Federated Learning Using AoI
An age-of-information Markov scheduling policy that balances client selection intervals is claimed to speed up federated learning convergence by 7.5-20% over random selection.