A token system where tokens expire and global models cost tokens forces strategic federated learning clients to adopt the server's acceptable privacy level.
What can we learn privately?
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
-
Strategic Incentivization for Locally Differentially Private Federated Learning
A token system where tokens expire and global models cost tokens forces strategic federated learning clients to adopt the server's acceptable privacy level.