Toward Seamless Hierarchical Federated Learning Under Intermittent Client Participation: A Stagewise Decision-Making Methodology
- 23 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (4) , 4715-4730
Abstract
Federated Learning (FL) offers a pioneering distributed learning paradigm that enables devices/clients to build a shared global model that can be obtained through frequent model transmissions between clients and a central server, causing high latency, energy consumption, and congestion over backhaul links. To overcome these drawbacks, Hierarchical Federated Learning (HFL) has emerged, which organizes clients into multiple clusters and utilizes edge nodes (e.g., edge servers) for intermediate model aggregations between clients and the central server. Current research on HFL mainly focus on enhancing model accuracy, latency, and energy consumption in scenarios with a stable/fixed set of clients. However, addressing the dynamic availability of clients – a critical aspect of real-world scenarios – remains underexplored. This study delves into optimizing client selection and client-to-edge associations in HFL under intermittent client participation so as to minimize overall system costs (i.e., delay and energy), while achieving fast model convergence. We unveil that achieving this goal involves solving a complex NP-hard problem. To tackle this, we propose a stagewise methodology that splits the solution into two stages, referred to as Plan A and Plan B. Plan A focuses on identifying long-term clients with high chance of participation in subsequent model training rounds. Plan B serves as a backup, selecting alternative clients when long-term clients are unavailable during model training rounds. This stagewise methodology offers a fresh perspective on client selection that can enhance both HFL and conventional FL via enabling low-overhead decision-making processes. Through evaluations on diverse datasets, we show that our methodology outperforms existing benchmarks on crucial factors such as model accuracy and system costs.Keywords
All Related Versions
This publication has 53 references indexed in Scilit:
- Hierarchical Federated Learning with Adaptive Clustering on Non-IID Data2022
- CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters2022
- Scattering Statistics of Generalized Spatial Poisson Point Processes2022
- Joint Client Selection and Task Assignment for Multi-Task Federated Learning in MEC Networks2021
- No routing needed between capsulesNeurocomputing, 2021
- Federated Learning for Internet of Things: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2021
- Hierarchical Federated Learning ACROSS Heterogeneous Cellular Networks2020
- Deep Residual Learning for Image Recognition2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Processor design for portable systemsJournal of Signal Processing Systems, 1996