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.
Methods compared.We compare KFCA to CA variants and to efficient Shapley value estimators; a brief description of each baseline is provided in Subsubsection A.11.6
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.