A parameter-free Bayesian aggregation method, based on variational inference over latent honesty indicators, matches Krum's robustness on benchmark federated learning attacks without needing to know the number of malicious clients.
Secureboost: A lossless federated learning framework
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
-
Bayesian Robust Aggregation for Federated Learning
A parameter-free Bayesian aggregation method, based on variational inference over latent honesty indicators, matches Krum's robustness on benchmark federated learning attacks without needing to know the number of malicious clients.