A norm-comparison payment rule makes truthful gradient reporting an approximately optimal strategy for clients in heterogeneous federated learning.
One for one, or all for all: Equilibria and optimality of collaboration in federated learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Incentivizing Truthful Collaboration in Heterogeneous Federated Learning
A norm-comparison payment rule makes truthful gradient reporting an approximately optimal strategy for clients in heterogeneous federated learning.