Yuzhong Ouyang

Yuzhong Ouyang

Auto-generated profile, based on publicly available information

Yuzhong Ouyang

Beijing Institute of Technology

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2026 in ACM Transactions on Internet of Things
Verified
Journal Article
Open access
YOYuzhong Ouyang
Yuzhong Ouyang
XWXiaoning Wu
Xiaoning Wu
MYMenglin Yang
Menglin Yang
Rui HanRui Han
Rui Han
ALAnjie Luo
Anjie Luo
YGYing Guo
Ying Guo
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.