Heterogeneity-Aware Dynamic Federated Split Learning with Adaptive Compression (HADFL-AC) Edge–Cloud Inference in IoT Environments
Open Access
- 17 April 2026
- journal article
- research article
- Published by MDPI AG in Future Internet
- Vol. 18 (4) , 213
Abstract
In resource-constrained environments, distributed split learning allows for collaborative training; however, the system suffers from high communication overhead and is sensitive to system heterogeneity. Despite advances in IoT data reduction and distributed learning, existing approaches treat heterogeneity, adaptability, and communication efficiency as separate problems. As a result, the Heterogeneity-Aware Dynamic Federated Split Learning with Adaptive Compression (HADFL-AC) framework is proposed, enabling adaptive adjustment of communication payloads to instantaneous bandwidth conditions during training. This approach distinguishes itself by focusing on feature-representation-level adaptation, offering seamless transitions between linear PCA, nonlinear Tiny Autoencoder (TinyAE), and hybrid PCA–AE compression methods without requiring changes to architecture or retraining. Experiments were conducted using the CIFAR10 and CI=NIC datasets with a lightweight ResNet-18 backbone under Dirichlet-based non-IID data partitioning and fluctuating network scenarios. HADFL-AC achieves significant communication reductions of 80.86% on CIFAR-10 and 77.2% on CINIC-10, as well as significant reductions in training time and energy consumption. In addition, the framework achieved these gains while maintaining competitive performance, reaching 79.58% on CIFAR-10 and exhibiting stable convergence on CINIC-10. Consequently, the results demonstrate that leveraging network heterogeneity as an adaptive signal facilitates efficient and scalable distributed learning while effectively balancing communication efficiency and model accuracy.Keywords
Funding Information
- Qassim University ((QU-J-PG-2-2025-53021))
This publication has 52 references indexed in Scilit:
- ARES: Adaptive Resource-Aware Split Learning for Internet of ThingsComputer Networks, 2022
- Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open ChallengesIEEE Communications Surveys & Tutorials, 2021
- Communication-efficient federated learningProceedings of the National Academy of Sciences, 2021
- Federated Learning in Mobile Edge Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2020
- SecOFF-FCIoT: Machine learning based secure offloading in Fog-Cloud of things for smart city applicationsInternet of Things, 2019
- An energy efficient IoT data compression approach for edge machine learningFuture Generation Computer Systems, 2019
- Distributed learning of deep neural network over multiple agentsJournal of Network and Computer Applications, 2018
- A Survey on Mobile Edge Computing: The Communication PerspectiveIEEE Communications Surveys & Tutorials, 2017
- Internet of Things: A Survey on Enabling Technologies, Protocols, and ApplicationsIEEE Communications Surveys & Tutorials, 2015
- Toward Social Internet of Vehicles: Concept, Architecture, and ApplicationsIEEE Access, 2015