KFCA is a strictly truthful incentive mechanism for federated learning using only categorical client reports under an honest majority, fixing label-flipping issues in prior Correlated Agreement methods.
• Stale Update (R1):The client submits the round-1 adapter update ∆θ1 s for all subsequent rounds, ignoring local training thereafter
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Knowledge-Free Correlated Agreement for Incentivizing Federated Learning
KFCA is a strictly truthful incentive mechanism for federated learning using only categorical client reports under an honest majority, fixing label-flipping issues in prior Correlated Agreement methods.