profile photo

Nannan Wu (吴南楠)

Dual Ph.D. Student

PolyU Logo

Department of Computing,

The Hong Kong Polytechnic University

HUST Logo

School of Electronic Information and Communications,

Huazhong University of Science and Technology

Email: <nannan.wu@connect.polyu.hk>, <wnn2000@hust.edu.cn>

google scholar github orcid linkedin

Short Bio

Currently, I am a dual Ph.D. student at the Department of Computing, The Hong Kong Polytechnic University (PolyU) and the School of Electronic Information and Communications, Huazhong University of Science and Technology (HUST). My doctoral research is guided by Prof. Changwen Chen, Prof. Li Yu, and Prof. Zengqiang Yan. Previously, I earned a B.Eng. degree from HUST in 2022.

My research interests are centered around trustworthy machine learning, with a current emphasis on federated learning.

News
Publications

clean-usnob

FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneity.
Zhaobin Sun*, Nannan Wu*, JunJie Shi, Li Yu, Kwang-Ting Cheng, Zengqiang Yan.
Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024.
(CCF Rank B) (Early Accept, top 11% in all submissions)
[paper] [code]

clean-usnob

FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completeness.
Yangyang Xiang*, Nannan Wu*, Li Yu, Xin Yang, Kwang-Ting Cheng, Zengqiang Yan.
Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024.
(CCF Rank B) (Early Accept, top 11% in all submissions)
[paper] [code]

clean-usnob

From Optimization to Generalization: Fair Federated Learning against Quality Shift via Inter-Client Sharpness Matching.
Nannan Wu, Zhuo Kuang, Zengqiang Yan, and Li Yu.
International Joint Conference on Artificial Intelligence (IJCAI), 2024.
(CCF Rank A) (Student Volunteer Program)
[paper] [code]

clean-usnob

FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise.
Nannan Wu, Zhaobin Sun, Zengqiang Yan, and Li Yu.
AAAI Conference on Artificial Intelligence (AAAI), 2024.
(CCF Rank A)
[paper] [code]

clean-usnob

DTMFormer: Dynamic Token Merging for Boosting Transformer-based Medical Image Segmentation.
Zhehao Wang, Xian Lin, Nannan Wu, Li Yu, Kwang-Ting Cheng, Zengqiang Yan.
AAAI Conference on Artificial Intelligence (AAAI), 2024.
(CCF Rank A)
[paper] [code]

clean-usnob

FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification.
Nannan Wu, Li Yu, Xin Yang, Kwang-Ting Cheng, and Zengqiang Yan.
Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2023.
(CCF Rank B) (Early Accept, top 14% in all submissions)
[paper] [code]

clean-usnob

FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity.
Nannan Wu, Li Yu, Xuefeng Jiang, Kwang-Ting Cheng, and Zengqiang Yan.
International Joint Conference on Artificial Intelligence (IJCAI), 2023.
(CCF Rank A)
[paper] [code]

Invited Talks
  • From Optimization to Generalization: Fair Federated Learning against Quality Shift via Inter-Client Sharpness Matching, at CSIG, May 2024. [Link (in Chinese)]
  • 面向不平衡医学图像的联邦带噪学习, at AI Time, Aug 2023. [Link (in Chinese)]
  • 标签质量感知的鲁棒联邦医学图像分割, at AI Time, Jan 2024. [Link (in Chinese)]
Professional Activities
  • Conference Service: Student Volunteer for IJCAI-24; Regular reviewers for PRCV-23, PRCV-24.
  • Journal Reviews: IEEE TETCI, Neural Networks
Selected Awards
  • PolyU Research Postgraduate Scholarship, in 2024.
  • Huazhong University of Science and Technology - China Optics Valley Morning Star Scholarship - Awarded to the top student among more than 400 undergraduates in the EIC, HUST, in 2021 (Top 0.25% award rate)
  • First Prize in the National Mathematics Competition for Undergraduate Students - Recognized nationally among peers, in 2020.
  • Zhuang Caifang & Zhuang Chongwen Scholarship - Awarded to one of the top students among over 200,000 high school graduates in Fujian Province, China, in 2018 (Top 0.1% award rate)