Stale Information Matters: Efficiently Tackling Data Heterogeneity in Asynchronous Federated Learning With Model Calibration
- 1 October 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47358-47369
Abstract
No abstract availableFunding Information
- Project “Research and Development of Heterogeneous Computing Center Inter-connection and Scheduling Software Stack” (YF202400000003)
- Hong Kong CRF (C7004-22G)
This publication has 16 references indexed in Scilit:
- Federated Analytics-Empowered Frequent Pattern Mining for Decentralized Web 3.0 Applications2024
- Asynchronous federated learning on heterogeneous devices: A surveyComputer Science Review, 2023
- A Reinforcement Learning Approach for Minimizing Job Completion Time in Clustered Federated Learning2023
- FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection2023
- A Hierarchical Knowledge Transfer Framework for Heterogeneous Federated Learning2023
- AOCC-FL: Federated Learning with Aligned Overlapping via Calibrated Compensation2023
- Toward Sustainable AI: Federated Learning Demand Response in Cloud-Edge Systems via Auctions2023
- KAFL: Achieving High Training Efficiency for Fast-K Asynchronous Federated Learning2022
- Federated Learning on Non-IID Data Silos: An Experimental Study2022
- Deep Residual Learning for Image Recognition2016