主动学习与标签高效学习
标注又贵又少的时候，挑哪些样本来标注、来训练、来迁移就很关键。这个方向研究怎么选数据，让模型用更少的监督信息达到可靠的性能
唐英鹏
南洋理工大学计算与数据科学学院 · 博士后研究员
我的研究关心一类很实际的问题：标记稀缺、数据分散、隐私受限、分布变化，这种情况下怎么把模型训好。具体方向包括主动学习、标签高效学习、迁移学习、联邦学习，以及药物发现中的人工智能
我目前在南洋理工大学计算与数据科学学院做博士后，在 Alvin Chan 教授的课题组开展研究工作。 本科、硕士和博士都毕业于 南京航空航天大学（2017、2020、2024），师从 黄圣君教授。 2017 到 2024 年，我在 PARNEC 组； 2024 到 2025 年，在 TrustFUL 实验室从事博士后研究，与 于涵教授合作； 2023 年，在 南洋理工大学数理科学学院（SPMS）访问交流，由 Yi Li 教授指导。
研究方向
面向标注稀缺、隐私受限与分布漂移场景的数据高效学习
软件
开源工具包
ALiPy: Active Learning in Python
ALiPy 提供了一套可复用的主动学习实验实现，内置多种查询策略和实验设置
论文发表
近期论文与代表性工作
完整列表见 Google Scholar
Federated Data and Feature Selection by Generalized CUR Decomposition.
Ying-Peng Tang, Zhuang Qi, Xiaoli Tang, Wei Zhuo, Sheng-Jun Huang, Han Yu.
In: Proceedings of the 43rd International Conference on Machine Learning, 2026.
Cross-View Lewis Weight Fusion Empowering Exemplar Replay for Federated Class-Incremental Learning.
Zhuang Qi, Ying-Peng Tang, Lei Meng, Xiaoxiao Li, Han Yu, Xiangxu Meng.
In: Proceedings of the 43rd International Conference on Machine Learning, 2026.
From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity.
Zhuang Qi, Ying-Peng Tang, Lei Meng, Guoqing Chao, Lei Wu, Han Yu, Xiangxu Meng.
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2026.
Class-wise Balancing Data Replay for Federated Class-Incremental Learning.
Zhuang Qi, Ying-Peng Tang, Lei Meng, Han Yu, Xiaoxiao Li, Xiangxu Meng.
In: Proceedings of the 39th Annual Conference on Neural Information Processing Systems, 2025.
Efficient Heterogeneity-Aware Federated Active Data Selection.
Ying-Peng Tang, Chao Ren, Xiaoli Tang, Sheng-Jun Huang, Lizhen Cui and Han Yu.
In: Proceedings of the 42nd International Conference on Machine Learning, 2025.
Active Learning for Multiple Target Models.
Sheng-Jun Huang, Yi Li and Ying-Peng Tang.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025.
QFEVAL: Quantum Federated Ensembled Variational Adaptive Learning for Dynamic Security Assessment in Cyber-Physical Systems.
Chao Ren, Ying-Peng Tang, Yulan Gao, Xian Sun, Kun Fu, Mikael Skoglund, Zhao Yang Dong, Han Yu, Anran Li, Ming Xiao.
In: IEEE Journal on Selected Areas in Communications, 2025.
One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models.
Sheng-Jun Huang, Yi Li, Yiming Sun and Ying-Peng Tang.
In: Proceedings of the 12th International Conference on Learning Representations, 2024.
MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection.
Dong Liang, Jing-Wei Zhang, Ying-Peng Tang and Sheng-Jun Huang.
In: IEEE Transactions on Geoscience and Remote Sensing, 2023.
Active Learning for Multiple Target Models.
Ying-Peng Tang and Sheng-Jun Huang.
In: Proceedings of the 36th Conference on Neural Information Processing Systems, 2022.
QBox: Partial Transfer Learning with Active Querying for Object Detection.
Ying-Peng Tang, Xiu-Shen Wei, Bo-Rui Zhao and Sheng-Jun Huang.
In: IEEE Transactions on Neural Networks and Learning Systems, 2021.
Dual Active Learning for Both Model and Data Selection.
Ying-Peng Tang and Sheng-Jun Huang.
In: Proceedings of the 30th International Joint Conference on Artificial Intelligence, 2021.
Self-paced active learning: query the right thing at the right time.
Ying-Peng Tang, Sheng-Jun Huang.
In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019.
学术履历
荣誉与学术服务
荣誉奖励
- 博士研究生国家奖学金
- 日内瓦国际发明展金奖
- 江苏省优秀学术学位硕士学位论文
- 中国国际“互联网+”大学生创新创业大赛银奖（队长）
- 硕士研究生国家奖学金
学术服务
会议审稿
AAAI、ICML、NeurIPS、CVPR、ICLR、IJCAI、SIGKDD 等。
期刊审稿
IEEE TKDE、Frontiers of Computer Science、Journal of Computer Science and Technology、Multimedia Systems 等。
程序委员会
FL@FM-TheWebConf（2025、2026）。