A validation-loss threshold with per-round payments keeps MNIST accuracy at 96.7% under 50% label-flipping adversaries, but the incentive-compatibility claim is a restatement of the payment rule.
Communication-efficient learning of deep networks from decentralized data,
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.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning
A validation-loss threshold with per-round payments keeps MNIST accuracy at 96.7% under 50% label-flipping adversaries, but the incentive-compatibility claim is a restatement of the payment rule.