Communication-Efficient Federated Learning with Adaptive Number of Participants

2025/08/19 by Sergey Skorik, Skorik, Sergey, Vladislav Dorofeev +11
Computer Science · Engineering · #Cooperative Communication and Network Coding #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Wireless Communication Security Techniques

paper · pdf · doi:10.48550/arxiv.2508.13803

openalex publication_date 2025/08/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Rapid scaling of deep learning models has enabled performance gains across domains, yet it introduced several challenges. Federated Learning (FL) has emerged as a promising framework to address these concerns by enabling decentralized training. Nevertheless, communication efficiency remains a key bottleneck in FL, particularly under heterogeneous and dynamic client participation. Existing methods, such as FedAvg and FedProx, or other approaches, including client selection strategies, attempt to mitigate communication costs. However, the problem of choosing the number of clients in a training round remains extremely underexplored. We introduce Intelligent Selection of Participants (ISP), an adaptive mechanism that dynamically determines the optimal number of clients per round to enhance communication efficiency without compromising model accuracy. We validate the effectiveness of ISP across diverse setups, including vision transformers, real-world ECG classification, and training with gradient compression. Our results show consistent communication savings of up to 30% without losing the final quality. Applying ISP to different real-world ECG classification setups highlighted the selection of the number of clients as a separate task of federated learning.

Citations

• FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers
• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
• Dynamic Attention-based Communication-Efficient Federated Learning
• Rethinking gradient sparsification as total error minimization
• Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
• Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies
• Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
• Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL
• Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective
• Adaptive Federated Optimization
• Advances and Open Problems in Federated Learning
• Active Federated Learning
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Federated Multi-Task Learning
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Revisiting Distributed Synchronous SGD
• Deep Residual Learning for Image Recognition
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Related

• Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning
• FedCliP: Federated Learning with Client Pruning
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• FedABC: Attention-Based Client Selection for Federated Learning with Long-Term View
• DPP-based Client Selection for Federated Learning with Non-IID Data