A distributed quantization mechanism for lightweight federated learning model in heterogeneous on-device AI networks
Authors:
- Misbah BibiMBMisbah Bibi
- Qazi Waqas KhanQKQazi Waqas Khan
- Syed Ali YazdanSYSyed Ali Yazdan
- Rashid AhmadRARashid Ahmad
- Do-Hyeun KimDKDo-Hyeun Kim
- 7 April 2026
- journal article
- Published by Elsevier in Information Processing & Management
- Vol. 63 (7)
Abstract
No abstract availableFunding Information
- Institute for Information and Communications Technology Promotion (R S-2025-02263031)
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea (RS-2024-00423362)
This publication has 22 references indexed in Scilit:
- PerFedGT: A personalized federated graph transformer for scale-heterogeneous graph dataInformation Processing & Management, 2025
- FedMWAD: Module-wise weighted aggregation federated learning combined with Ditto for patient-independent seizure predictionInformation Processing & Management, 2025
- Consensus-Driven Hyperparameter Optimization for Accelerated Model Convergence in Decentralized Federated LearningInternet of Things, 2024
- Personalized hierarchical heterogeneous federated learning for thermal comfort prediction in smart buildingsEngineering Applications of Artificial Intelligence, 2024
- Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices2024
- Adaptive DFL‐based straggler mitigation mechanism for synchronous ring topology in digital twin networksIET Collaborative Intelligent Manufacturing, 2024
- A precision-centric approach to overcoming data imbalance and non-IIDness in federated learningInternet of Things, 2023
- Decentralized Machine Learning Training: A Survey on Synchronization, Consolidation, and TopologiesIEEE Access, 2023
- RepVGG: Making VGG-style ConvNets Great Again2021
- Recurrent Neural Networks for Multivariate Time Series with Missing ValuesScientific Reports, 2018