Monotonicity of aggregated gradients holds if and only if the aggregation rule is positively affine; non-affine rules therefore prevent steady convergence and degrade stability.
Dp-brem: differentially-private and byzantine-robust federated learning with client momentum
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
FLARE uses adaptive multi-dimensional reputation scores and soft exclusion to improve Byzantine robustness in federated learning by up to 16% over prior methods while handling a new Statistical Mimicry attack.
citing papers explorer
-
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Monotonicity of aggregated gradients holds if and only if the aggregation rule is positively affine; non-affine rules therefore prevent steady convergence and degrade stability.
-
FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
FLARE uses adaptive multi-dimensional reputation scores and soft exclusion to improve Byzantine robustness in federated learning by up to 16% over prior methods while handling a new Statistical Mimicry attack.