FedSteer constructs a gradient subspace from cached client updates, projects active gradients to obtain coordinates, and reuses those coordinates on the drifted subspace to correct extreme staleness in federated learning.
Towards optimal heterogeneous client sampling in multi-model feder- ated learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The paper derives the first convergence upper bound for split federated learning under activation upload, gradient download, and aggregation failures, then jointly optimizes client sampling and model splitting to minimize the bound, with simulations on EMNIST and CIFAR-10.
citing papers explorer
-
FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching
FedSteer constructs a gradient subspace from cached client updates, projects active gradients to obtain coordinates, and reuses those coordinates on the drifted subspace to correct extreme staleness in federated learning.
-
Optimizing Split Federated Learning with Unstable Client Participation
The paper derives the first convergence upper bound for split federated learning under activation upload, gradient download, and aggregation failures, then jointly optimizes client sampling and model splitting to minimize the bound, with simulations on EMNIST and CIFAR-10.