Yuzhong Ouyang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuzhong Ouyang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Anjie Luo
Beijing Institute of Technology
1 shared publication - Chi Harold Liu
Beijing Institute of Technology
1 shared publication - Jing Chen
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
1 shared publication - Menglin Yang
Beijing Institute of Technology
1 shared publication - Rui Han
Beijing Institute of Technology, Beijing, China
1 shared publication - Xiaoning Wu
Beijing Institute of Technology
1 shared publication
Latest Publications
- Open Access
- 9 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Internet of Things
- Vol. 7 (2) , 1-22
EdgeTail: Mitigating Long-Tail Visual Problems in Continual Learning at Edge
Large vision and language models deployed at edge encounter continuously evolving input distributions, including not only new tasks but also highly unbalanced long-tail classes. For example, smart-surveillance cameras frequently capture common objects such as pedestrians and cars, while only occasionally observing tail classes like horseback riders or stroller pushers. However, most existing long-tail mitigation techniques are designed for fixed pretraining data. This often leads to poor accuracy of tail classes on evolving data and incurs high computational costs on edge devices. In this article, we propose EdgeTail, a lightweight long-tail mitigation method for edge-side continual learning. EdgeTail’s key design features are: (i) optimal long-tailed mitigation solution search, which adaptively selects the best long-tail learning method for the current distribution/task; and (ii) graph attention classifier and multi-branch adapter, which improves the quality and stability of tail class representations with small overheads. We implement EdgeTail in PyTorch and extensively evaluate it against state-of-the-art methods. The results show that EdgeTail improves the average accuracy by 36.09% under fixed training windows and by 31.12% under different training window sizes.
- 9 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Internet of Things
- Vol. 7 (2) , 1-22
Open AccessEdgeTail: Mitigating Long-Tail Visual Problems in Continual Learning at Edge
Large vision and language models deployed at edge encounter continuously evolving input distributions, including not only new tasks but also highly unbalanced long-tail classes. For example, smart-surveillance cameras frequently capture common objects such as pedestrians and cars, while only occasionally observing tail classes like horseback riders or stroller pushers. However, most existing long-tail mitigation techniques are designed for fixed pretraining data. This often leads to poor accuracy of tail classes on evolving data and incurs high computational costs on edge devices. In this article, we propose EdgeTail, a lightweight long-tail mitigation method for edge-side continual learning. EdgeTail’s key design features are: (i) optimal long-tailed mitigation solution search, which adaptively selects the best long-tail learning method for the current distribution/task; and (ii) graph attention classifier and multi-branch adapter, which improves the quality and stability of tail class representations with small overheads. We implement EdgeTail in PyTorch and extensively evaluate it against state-of-the-art methods. The results show that EdgeTail improves the average accuracy by 36.09% under fixed training windows and by 31.12% under different training window sizes.