Introduces MEB and c-MEB validity conditions for Byzantine-robust aggregation, proving achievability under majority honesty (n>2t) with an optimal MinMax-MEB rule at c<sqrt(2) and explicit guarantees for standard aggregators.
Approximate agreement algorithms for byzantine collaborative learning
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
-
Practical Validity Conditions for Byzantine-Tolerant Federated Learning
Introduces MEB and c-MEB validity conditions for Byzantine-robust aggregation, proving achievability under majority honesty (n>2t) with an optimal MinMax-MEB rule at c<sqrt(2) and explicit guarantees for standard aggregators.