Wenju Sun
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenju Sun has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Wen Wang
Beijing Jiaotong University
5 shared publications - Qingyong Li
Beijing Jiaotong University
4 shared publications - Yangli-Ao Geng
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing 100044, China
4 shared publications - Siyu Zhang
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Ministry of Education), Beijing Jiaotong University, Beijing, Beijing, China
3 shared publications Qingyong Li
2 shared publications- Boyang Li
College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (10) , 9257-9267
CKM: Continual Anomaly Detection Based on Compact Knowledge Memory
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (10) , 9257-9267
CKM: Continual Anomaly Detection Based on Compact Knowledge Memory
- 20 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 174
Towards plastic and stable incremental learning: A dual-learner framework with cumulative parameter averaging
- 20 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 174
Towards plastic and stable incremental learning: A dual-learner framework with cumulative parameter averaging
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5178-5187
Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5178-5187
Open AccessTask Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
- 5 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 653
Decoupled likelihood modeling: A scalable approach for incremental generalized category discovery
- 5 August 2025
- Published by Elsevier in Neurocomputing
- Vol. 653
Decoupled likelihood modeling: A scalable approach for incremental generalized category discovery
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4292-4301
Incremental Learning via Robust Parameter Posterior Fusion
The posterior estimation of parameters based on Bayesian theory is a crucial technique in Incremental Learning (IL). The estimated posterior is typically utilized to impose loss regularization, which aligns the current training model parameters with the previously learned posterior to mitigate catastrophic forgetting, a major challenge in IL. However, this additional loss regularization can also impose detriment to the model learning, preventing it from reaching the true global optimum. To overcome this limitation, this paper introduces a novel Bayesian IL framework, Robust Parameter Posterior Fusion (RP2F). Unlike traditional methods, RP2F directly estimates the parameter posterior for new data without introducing extra loss regularization, which allows the model to accommodate new knowledge more sufficiently. It then fuses this new posterior with the existing ones based on the Maximum A Posteriori (MAP) principle, ensuring effective knowledge sharing across tasks. Furthermore, RP2F incorporates a common parameter-robustness priori to facilitate a seamless integration during posterior fusion. Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets show that RP2F not only effectively mitigates catastrophic forgetting but also achieves backward knowledge transfer.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 4292-4301
Open AccessIncremental Learning via Robust Parameter Posterior Fusion
The posterior estimation of parameters based on Bayesian theory is a crucial technique in Incremental Learning (IL). The estimated posterior is typically utilized to impose loss regularization, which aligns the current training model parameters with the previously learned posterior to mitigate catastrophic forgetting, a major challenge in IL. However, this additional loss regularization can also impose detriment to the model learning, preventing it from reaching the true global optimum. To overcome this limitation, this paper introduces a novel Bayesian IL framework, Robust Parameter Posterior Fusion (RP2F). Unlike traditional methods, RP2F directly estimates the parameter posterior for new data without introducing extra loss regularization, which allows the model to accommodate new knowledge more sufficiently. It then fuses this new posterior with the existing ones based on the Maximum A Posteriori (MAP) principle, ensuring effective knowledge sharing across tasks. Furthermore, RP2F incorporates a common parameter-robustness priori to facilitate a seamless integration during posterior fusion. Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets show that RP2F not only effectively mitigates catastrophic forgetting but also achieves backward knowledge transfer.
- 2 August 2023
- Published by Elsevier in Neurocomputing
- Vol. 556
Class Incremental Learning based on Identically Distributed Parallel One-Class Classifiers
- 2 August 2023
- Published by Elsevier in Neurocomputing
- Vol. 556
Class Incremental Learning based on Identically Distributed Parallel One-Class Classifiers