AFBS scores buffered gradients by staleness and dataset size, discards low-value ones, and clusters clients through random-projection-encrypted label distributions before aggregation in semi-asynchronous federated learning.
Straggler-resilient federated learning: Leveraging the interplay between statistical accuracy and system heterogeneity,
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
-
AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning
AFBS scores buffered gradients by staleness and dataset size, discards low-value ones, and clusters clients through random-projection-encrypted label distributions before aggregation in semi-asynchronous federated learning.