Chang-E Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chang-E Ren has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Chun Lung Philip Chen
South China University of Technology
4 shared publications Siyao Cheng
3 shared publications- Tao Du
School of Information Science and Technology, North China University of Technology, Beijing, China
3 shared publications Yong Guan
College of Information Engineering, Capital Normal University, Beijing, China
3 shared publicationsGuilu Li
2 shared publications- Jiamin Ji2 shared publications
Latest Publications
- 25 March 2026
- Published by Elsevier in Neurocomputing
- Vol. 682
Privacy-preserving decentralized federated broad continuous learning based on complete binary tree
- 25 March 2026
- Published by Elsevier in Neurocomputing
- Vol. 682
Privacy-preserving decentralized federated broad continuous learning based on complete binary tree
- 23 January 2026
- Published by Springer Nature
- p. 500-513
Polarization Image Enhancement Method Based on Federated Learning
- 23 January 2026
- Published by Springer Nature
- p. 500-513
Polarization Image Enhancement Method Based on Federated Learning
- 19 January 2026
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 69 (5) , 838-851
Personalized federated learning with feature complementarity and temporal regularization
Personalized federated learning aims to deliver customized models for clients with heterogeneous data distributions while preserving data privacy. In this work, we propose personalized federated learning with feature complementarity and temporal regularization (pFedCT), a novel PFL framework where each client adopts a broad learning system (BLS) as the local model. Indeed, the existing BLS-based FL methods have been successful in enhancing communication efficiency, privacy preservation, and Byzantine robustness, but they often fail to address the critical issue of personalization. To achieve effective personalization, pFedCT introduces two key components. First, we extract feature node matrices from each client’s BLS model, which capture the internal feature representations of local data. By comparing the principal subspaces of these matrices, we assess the complementarity between clients’ learned representations. This enables each client to collaborate with others who provide diverse and informative knowledge. Second, we incorporate a temporal regularization mechanism to stabilize the collaboration structure across communication rounds, mitigating performance degradation caused by fluctuating local updates and data shifts. Extensive experiments on Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets under both independent and identically distributed (IID) and non-IID settings demonstrate that pFedCT consistently outperforms existing BLS-based baselines and achieves competitive accuracy compared to deep neural network-based methods, while maintaining superior efficiency in communication and computation.
- 19 January 2026
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 69 (5) , 838-851
Personalized federated learning with feature complementarity and temporal regularization
Personalized federated learning aims to deliver customized models for clients with heterogeneous data distributions while preserving data privacy. In this work, we propose personalized federated learning with feature complementarity and temporal regularization (pFedCT), a novel PFL framework where each client adopts a broad learning system (BLS) as the local model. Indeed, the existing BLS-based FL methods have been successful in enhancing communication efficiency, privacy preservation, and Byzantine robustness, but they often fail to address the critical issue of personalization. To achieve effective personalization, pFedCT introduces two key components. First, we extract feature node matrices from each client’s BLS model, which capture the internal feature representations of local data. By comparing the principal subspaces of these matrices, we assess the complementarity between clients’ learned representations. This enables each client to collaborate with others who provide diverse and informative knowledge. Second, we incorporate a temporal regularization mechanism to stabilize the collaboration structure across communication rounds, mitigating performance degradation caused by fluctuating local updates and data shifts. Extensive experiments on Modified National Institute of Standards and Technology (MNIST) and Fashion-MNIST datasets under both independent and identically distributed (IID) and non-IID settings demonstrate that pFedCT consistently outperforms existing BLS-based baselines and achieves competitive accuracy compared to deep neural network-based methods, while maintaining superior efficiency in communication and computation.
- 9 January 2026
- Published by Elsevier in Computer Networks
- Vol. 276
FLSC: A semantic-guided heterogeneous federated learning with cascading heterogeneity compensation
- 9 January 2026
- Published by Elsevier in Computer Networks
- Vol. 276
FLSC: A semantic-guided heterogeneous federated learning with cascading heterogeneity compensation
- 19 December 2025
- Published by Springer Nature in Control Theory and Technology
- Vol. 24 (3) , 327-345
Security consensus control for nonlinear stochastic multi-agent systems via reinforcement learning
- 19 December 2025
- Published by Springer Nature in Control Theory and Technology
- Vol. 24 (3) , 327-345
Security consensus control for nonlinear stochastic multi-agent systems via reinforcement learning
- 3 November 2025
- Published by Elsevier in Computer Networks
- Vol. 274
FBL-HA: A hybrid aggregation scheme for heterogeneous federated broad learning
- 3 November 2025
- Published by Elsevier in Computer Networks
- Vol. 274
FBL-HA: A hybrid aggregation scheme for heterogeneous federated broad learning
- 25 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 654
FOATLBL: Federated online active transfer learning via broad learning system
- 25 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 654
FOATLBL: Federated online active transfer learning via broad learning system
- 18 March 2025
- Published by Elsevier in Neurocomputing
- Vol. 636
Privacy-preserving and Byzantine-robust federated broad learning with chain-loop structure
- 18 March 2025
- Published by Elsevier in Neurocomputing
- Vol. 636
Privacy-preserving and Byzantine-robust federated broad learning with chain-loop structure
- 26 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (8) , 4592-4604
Adaptive Impulsive Consensus of Nonlinear Multiagent Systems With Limited Bandwidth Under Uncertain Deception Attacks
At present, the dynamic encoding–decoding scheme is utilized in the impulsive consensus control of multiagent systems (MASs) to solve the limited bandwidth problem. However, the unknown nonlinear dynamics and deception attacks will generate some uncertainties inevitably in the encoding–decoding, which may cause the quantizer saturation and then influence the consensus performance. Therefore, the impulsive consensus control problem of uncertain nonlinear MASs based on encoding–decoding under deception attacks is investigated in this article. To address the system uncertainty, an adaptive algorithm with neural networks is designed. Under the proposed estimator for each follower, the designed adaptive law for every follower only needs the information from its own sensor and estimator instead of the quantized information from its neighbors. Then a more general scenario of uncertain deception attack is considered, in which the uncertain deception attacks can occur in the both parts of hybrid impulsive control protocol. An attack observer is introduced to handle this more complex attack by compensating impacts of deception attacks. Next the sufficient conditions for secure consensus of MASs with limited bandwidth are derived. Moreover, although some uncertainties exist in the encoding–decoding, the quantizer saturation can be eliminated by adjusting the parameters of controller. Finally, the validity of given theorems is demonstrated by the simulation experiments.
- 26 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (8) , 4592-4604
Adaptive Impulsive Consensus of Nonlinear Multiagent Systems With Limited Bandwidth Under Uncertain Deception Attacks
At present, the dynamic encoding–decoding scheme is utilized in the impulsive consensus control of multiagent systems (MASs) to solve the limited bandwidth problem. However, the unknown nonlinear dynamics and deception attacks will generate some uncertainties inevitably in the encoding–decoding, which may cause the quantizer saturation and then influence the consensus performance. Therefore, the impulsive consensus control problem of uncertain nonlinear MASs based on encoding–decoding under deception attacks is investigated in this article. To address the system uncertainty, an adaptive algorithm with neural networks is designed. Under the proposed estimator for each follower, the designed adaptive law for every follower only needs the information from its own sensor and estimator instead of the quantized information from its neighbors. Then a more general scenario of uncertain deception attack is considered, in which the uncertain deception attacks can occur in the both parts of hybrid impulsive control protocol. An attack observer is introduced to handle this more complex attack by compensating impacts of deception attacks. Next the sufficient conditions for secure consensus of MASs with limited bandwidth are derived. Moreover, although some uncertainties exist in the encoding–decoding, the quantizer saturation can be eliminated by adjusting the parameters of controller. Finally, the validity of given theorems is demonstrated by the simulation experiments.