Energy-Efficient Personalized Federated Continual Learning on Edge
- 5 December 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 16 (4) , 345-348
Abstract
Federated learning (FL) on the edge devices must support continual learning (CL) to handle continuously evolving the data and perform the model training in an energy-efficient manner to accommodate the devices with limited computational and energy resources. This letter proposes an energy-efficient personalized federated CL (FCL) framework for the edge devices. The network structure on each device is divided into parts for retaining old knowledge and learning new knowledge, training only part of the model to reduce overhead. A data-free parameter selection approach selects important parameters from the trained model to retain old knowledge. During new task learning, a federated search method determines a resource-adaptive personalized model structure for each device. Experimental results demonstrate that our method can effectively support FCL in an energy-efficient manner on the edge devices.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities, CHD (300102374102)
This publication has 9 references indexed in Scilit:
- CaloFlow for CaloChallenge dataset 1SciPost Physics, 2024
- Continual Horizontal Federated Learning for Heterogeneous Data2022
- Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning2021
- Advances and Open Problems in Federated LearningFoundations and Trends in Machine Learning, 2021
- Class-incremental Learning via Deep Model Consolidation2020
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning2018
- Learning without ForgettingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012