FedPCS uses a Stackelberg game and mean-field estimation to set client sampling probabilities and rewards from privacy budgets, claiming a bounded price of anarchy and better federated learning accuracy.
A novel incentive mechanism for federated learning over wireless communications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.GT 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A Game-Theoretic Framework for Privacy-Aware Client Sampling in Federated Learning
FedPCS uses a Stackelberg game and mean-field estimation to set client sampling probabilities and rewards from privacy budgets, claiming a bounded price of anarchy and better federated learning accuracy.