D-Byz-SGDM aggregates cached momentum from non-sampled clients together with fresh momentum from sampled clients, preserving Byzantine robustness under partial participation and achieving an optimal O(cδζ²/p) stationary error.
Byzantine-resilient non-convex stochastic gradient descent
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
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation
D-Byz-SGDM aggregates cached momentum from non-sampled clients together with fresh momentum from sampled clients, preserving Byzantine robustness under partial participation and achieving an optimal O(cδζ²/p) stationary error.