Could Model Partitioning Make Federated Learning More Sustainable?

Lightweight Aggregation Protocols for Green Federated Learning in Vehicle-to-Cloud Systems

Exploring aggregation strategies for federated learning in national statistics 1

A weighted Federated Averaging aggregation scheme which aims to highlight the potential benefits of positively weighing clients who contain more homogeneous data and the preliminary results exhibit that when clients with more homogeneous data are weighed higher, the global model can achieve better performance, but that...

Optimizing Federated Learning Efficiency via Slimmable Neural Networks and AirComp for Resource-Heterogeneous Devices

The Air-FedSNN framework, which integrates slimmable neural networks (SNNs) with over-the-air computation (AirComp) to improve communication, computation, and energy efficiency in heterogeneous IoT networks, and provides an efficient solution for resource-constrained environments.

FedQS: asynchronous federated learning based on queue scheduling

An asynchronous framework named FedQS, which employs a multi-dimensional staleness evaluation mechanism that dynamically assesses updates by combining the similarity between local and global models with client latency metrics, and implements a decoupling solution via a queue scheduling algorithm to resolve the coupling...

FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices

The Federated Parallel Scaling (FPS) algorithm is proposed, which jointly trains multiple sampled subnetworks in parallel with self-distillation so that larger sampled subnetworks can supervise smaller ones during local updates.

Scalable Data Engineering Architectures for Federated Learning in Decentralized Cloud Environments

This paper presents a comprehensive architectural framework for scalable data engineering tailored for FL in heterogeneous and resource-constrained environments and proposes a modular architecture that addresses data heterogeneity, scalability, and compliance.