analiza aiqbench
SHEFL introduces a novel federated learning framework that optimizes system heterogeneity by leveraging high-power clients to train global ensemble members while low-power clients focus on assigned tasks. This approach resolves common issues like biased aggregation and excessive uplink demand, achieving significant accuracy gains over existing methods under constrained communication budgets. The technique advances distributed machine learning efficiency without relying on quantum mechanics or general consumer electronics trends.
SHEFL: Sparse Heterogeneous Ensemble Federated Learning with Group-Balanced Aggregation
arXiv:2508.08552v3 Announce Type: replace Abstract: System heterogeneity in federated learning (FL) requires training workloads and communication demands to be adapted to client resource capacities. Federated ensemble learning distributes multiple predictors across clients, but assigning one ensemble member to each client reduces the number of contributors to each member as the ensemble grows. We propose SHEFL, a global ensemble-based FL framework that uses the additional computation of high-power clients (HPCs) to train all ensemble members while low-power clients (LPCs) train one assigned member. SHEFL addresses increased HPC uplink demand and biased aggregation toward HPC updates through resource-aware sparse update allocation and group-balanced aggregation. Across four vision datasets, SHEFL improves over Fed-Ensemble (FedEns) in all data heterogeneity settings. Under a matched total uplink budget, SHEFL reaches the target accuracy in fewer rounds than FedEns and improves final accuracy by up to 14.65 points. Ablations further show that group-balanced aggregation improves accuracy and convergence under different resource allocations.
Abstract:System heterogeneity in federated learning (FL) requires training workloads and communication demands to be adapted to client resource capacities. Federated ensemble learning distributes multiple predictors across clients, but assigning one ensemble member to each client reduces the number of contributors to each member as the ensemble grows. We propose SHEFL, a global ensemble-based FL framework that uses the additional computation of high-power clients (HPCs) to train all ensemble members while low-power clients (LPCs) train one assigned member. SHEFL addresses increased HPC uplink demand and biased aggregation toward HPC updates through resource-aware sparse update allocation and group-balanced aggregation. Across four vision datasets, SHEFL improves over Fed-Ensemble (FedEns) in all data heterogeneity settings. Under a matched total uplink budget, SHEFL reaches the target accuracy in fewer rounds than FedEns and improves final accuracy by up to 14.65 points. Ablations further show that group-balanced aggregation improves accuracy and convergence under different resource allocations.
Machine Learning (cs.LG); Distributed, Parallel, and Cluster Computing (cs.DC)
arXiv:2508.08552 [cs.LG]
(or arXiv:2508.08552v3 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2508.08552 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 248 cuvinte
Subiecte conexe
MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning
arXiv · 18 aug. 2026
H-FedSN: Personalized Sparse Networks for Efficient and Accurate Hierarchical Federated Learning for IoT Applications
arXiv · 1 sept. 2026
Task-Aware Federated Fine-Tuning for MoE-based Large Language Models
arXiv · 16 sept. 2026
MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneity
arXiv · 17 aug. 2026