March 3, 2026

CosAge: Federated Learning with Gradient Summaries for Centralized Client Selection

Key Points

The CosAge model enhances client selection in federated learning, outperforming traditional methods.
Simulation results indicate that CosAge performs better in non-IID settings than both AoI-only and dissimilarity-only methods.
Using gradient summaries, this approach reduces the need for full client statistics or direct coordination.
CosAge highlights the importance of efficient resource management in federated learning systems.

Abstract

Heterogeneous data and partial participation hinder the effectiveness of federated learning (FL). To compare client selection policies under a common yardstick, we adopt the Federated Learning with Gradient Summaries for Centralized Client Selection (FL-GSCCS) model, where each client transmits a lightweight gradient summary for selection and only chosen clients perform full local training with sparsified updates. Within this framework, we propose C OS A GE , a hybrid centralized policy that combines Age of Information (AoI) with gradient dissimilarity computed from a proxy update via the cos 4 metric. Simulation results show that C OS A GE consistently outperforms AoI-only and dissimilarity-only baselines in non-IID settings, and approaches the performance of clustering-based upper bounds without requiring client-to-client coordination or server access to client statistics.

CosAge: Federated Learning with Gradient Summaries for Centralized Client Selection

Key Points

Abstract

Cite This Study