High-Performance Personalized Federated Continual Learning Framework for Dynamic Data Sharing in IoV
- 14 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (8) , 15265-15279
Abstract
The Internet of Vehicles (IoV) connects vehicles to the internet, delivering smarter and more convenient mobility services to users. Traditional intelligent service models typically employ federated learning (FL) for training. However, as vehicles continuously encounter new data and exhibit heterogeneous computational capabilities, these models often suffer from catastrophic forgetting and performance degradation. To address the above challenges, this article focuses on training a personalized federated continual learning (PFCL) model that is expected to achieve good performance on all local tasks. The new PFCL scheme, called adaptive PFCL (Adp-PFCL), handles catastrophic forgetting and the lack of personalized solutions. In Adp-PFCL: 1) each vehicle client uses the online continual learning (OCL) algorithm to train its local model in the local training stage to mitigate the forgetting of old knowledge; and 2) during the local model update phase, each vehicle client locally executes the privacy-preserving federated deep mutual learning (PP-FedDML) strategy to facilitate personalization and improve the performance of the global model on local data. Extensive experimental results demonstrate that the Adp-PFCL scheme achieves at least a 28.36% improvement in average accuracy while reducing runtime by 7.75% compared with current mainstream approaches, validating its high adaptability to dynamic data and computational efficiency.Keywords
Funding Information
- High-Quality Development and Industrial Foundation Reconstruction Project of the Ministry of Industry and Information Technology of China (0747-2361SCCZA204)
- National Natural Science Foundation of China (62233003)
This publication has 25 references indexed in Scilit:
- Federated Incremental Semantic Segmentation2023
- Federated Class-Incremental Learning2022
- Maintaining Discrimination and Fairness in Class Incremental Learning2020
- Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning2019
- Large Scale Incremental Learning2019
- Task-Free Continual Learning2019
- Memory Aware Synapses: Learning What (not) to Forget2018
- Deep Mutual Learning2018
- iCaRL: Incremental Classifier and Representation Learning2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences of the United States of America, 2017