Chao Wu / 吴超

Chao Wu is a Research Professor at School of Public Affairs, Zhejiang University. He is now the director of Computational Social Science Research Center (ZJUCCS). He is also a Honorary Research Fellow of Data Science Institute and Department of Computing, Imperial College London, and the Director of Big Data Research Center - ZJPTCC. 吴超，浙江大学公共管理学院研究员（博士生导师）。现任浙江大学计算社会科学研究中心（ZJUCCS）主任，同时担任英国帝国理工学院数据科学研究所及计算机系荣誉研究员，以及浙江省公共政策研究院大数据研究中心主任。 His main research interests is about distributed machine learning, privacy protection, and computable social analytics. A list of selected publications is available here. He is also the creator of Mo, which is web-based platform for both AI modelling and eduction. 主要研究方向包括分布式机器学习、隐私保护和可计算社会分析。部分发表论文列表可在此处查看。他同时也是 Mo 平台的创始人，该平台是一个面向人工智能建模和教育的在线平台。

Research研究方向

• Distributed AI (Galaxy Learning)分布式人工智能（星云学习）: A decentralized machine learning methodology based on Federated Learning. The research focuses on joint modelling for non-IID data, privacy protection, and data ownership and pricing. We are also developing an open source framework for it.一种基于联邦学习的去中心化机器学习方法。研究重点包括非独立同分布数据的联合建模、隐私保护以及数据确权与定价。我们同时在开发相关的开源框架。
• Computable Social Analytics: Data driven methodology for social science research, including intelligent transportation, smart cites, and neuro-management, etc. We established ZJUCCS as a hub for this research.

• Lu, C., Guo, C., Li, Z., Wu, C., Liu, T., & Lu, Y. (2026). Multi-graph based neural architecture search for robust recommendation. CoRR.
• Luo, S., Ren, H., Zhang, J., Zhou, L., Li, C., Ma, T., & Wu, C. (2025). Beyond centralized fairness adaptation: Dynamic fairness in decentralized federated learning with reinforcement learning. Expert Systems with Applications, 268, 126365.
• Shen, T., Wu, C., Liang, J., Wang, C., Wang, Z., Zhang, H., Li, C., & Yan, M. (2025). FedMcon: Let federated learning model know what they should know. Frontiers of Information Technology & Electronic Engineering.
• Gao, Y., Zhou, T., Pan, C., Shen, T., Wu, C., Wang, C., & Hu, S. (2025). FediOS: Privacy-preserving federated out-of-distribution generalization under system heterogeneity. Machine Learning, 114(5), 2011-2045.
• Wu, C., Zhang, H., Wang, C., Shen, T., Huo, C., & Li, C. (2025). Managing data quality for decentralized machine learning systems. IEEE Transactions on Services Computing, 18(3), 1055-1068.
• Huang, B., Chen, H., Shen, T., Hu, Y., Wu, C., Xiao, J., & Song, D. (2025). Federated class incremental learning with domain shift as online learning under non-IID labels and features. Findings of ACL 2025.
• Zhu, S., Huang, B., Shen, T., Wu, C., Xiao, J., Song, D., & Qin, Z. (2025). Decentralized federated learning with foundation models and agentic graph reinforcement learning. In ICLR 2025.
• Zhang, J., Shen, T., Wang, C., Han, K., Wu, C., & Xiao, J. (2025). Rational and efficient federated graph learning with synthetic graph coarsening and data leakage prevention. In IJCAI 2025.
• Li, Y., Wang, C., Shen, T., Sun, Y., Huang, B., Wu, C., & Xiao, J. (2025). FedGuCci: Curvature-informed Gaussian unified clustering in federated learning under unknown participation constraints. In KDD 2025.
• Wu, S., Liwang, M., Wang, D., Wang, X., Wu, C., Tang, J., Li, L., & Jiao, Z. (2025). Effective Two-Stage Double Auction for Dynamic Resource Trading in Edge Networks via Overbooking. CoRR abs/2501.04507.
• Huang, Y., Liu, C., Feng, Y., Wu, C., Wu, F., & Kuang, K. (2025). Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction. CoRR abs/2502.11084.
• Yan, S., Li, Z., Wu, C., Pang, M., Lu, Y., Yan, Y., & Wang, H. (2025). You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data. CoRR abs/2503.06916.
• Li, Z., Lin, J., Li, Z., Zhu, D., & Wu, C. (2024). Improving Group Connectivity for Generalization of Federated Deep Learning. CoRR abs/2402.18949.
• Yao, J., Zhang, S., Yao, Y., Wang, F., Ma, J., Zhang, J., Chu, Y., Ji, L., Jia, K., Shen, T., Wu, A., Zhang, F., Tan, Z., Kuang, K., Wu, C., Wu, F., Zhou, J., & Yang, H. (2023). Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI. IEEE Transactions on Knowledge and Data Engineering, 35(7), 6866-6886.
• Li, Z., Li, Q., Zhou, Y., Zhong, W., Zhang, G., & Wu, C. (2023). Edge-cloud Collaborative Learning with Federated and Centralized Features. SIGIR 2023, 1949-1953.
• Zhu, D., Li, Y., Shao, Y., Hao, J., Wu, F., Kuang, K., Xiao, J., & Wu, C. (2023). Generalized Universal Domain Adaptation with Generative Flow Networks. CoRR abs/2305.04466.
• Zhang, J., Li, B., Chen, C., Lyu, L., Wu, S., Ding, S., & Wu, C. (2023). Delving into the Adversarial Robustness of Federated Learning. CoRR abs/2302.09479.
• Shen, T., Zhang, J., Jia, X., Zhang, F., Lv, Z., Kuang, K., Wu, C., & Wu, F. (2023). Federated mutual learning: a collaborative machine learning method for heterogeneous data, models, and objectives. Frontiers of Information Technology & Electronic Engineering, 24(10), 1390-1402.
• Zhang, J., Chen, C., Li, B., Lyu, L., Wu, S., Ding, S., Shen, C., & Wu, C. (2022). DENSE: Data-Free One-Shot Federated Learning. NeurIPS 2022.
• Wang, B., Li, G., Wu, C., Zhang, W., Zhou, J., & Wei, Y. (2022). A framework for self-supervised federated domain adaptation. EURASIP Journal on Wireless Communications and Networking, 2022(1), 1-17.
• Zhang, J., Li, Z., Li, B., Xu, J., Wu, S., Ding, S., & Wu, C. (2022, June). Federated Learning with Label Distribution Skew via Logits Calibration. In International Conference on Machine Learning (pp. 26311-26329). PMLR.
• Luo, S., Li, Y., Li, J., Kuang, K., Liu, F., Shao, Y., & Wu, C. (2022). S2RL: Do We Really Need to Perceive All States in Deep Multi-Agent Reinforcement Learning?. arXiv preprint arXiv:2206.11054.
• Yao, J., Zhang, S., Yao, Y., Wang, F., Ma, J., Zhang, J., ... & Yang, H. (2022). Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI. IEEE Transactions on Knowledge and Data Engineering.
• Wang, Z., Hu, Y., Yan, S., Wang, Z., Hou, R., & Wu, C. (2022). Efficient Ring-Topology Decentralized Federated Learning with Deep Generative Models for Medical Data in eHealthcare Systems. Electronics, 11(10), 1548.
• Taleongpong, P., Hu, S., Jiang, Z., Wu, C., Popo-Ola, S., & Han, K. (2022). Machine learning techniques to predict reactionary delays and other associated key performance indicators on British railway network. Journal of Intelligent Transportation Systems, 26(3), 311-329.
• Li, Z., Lu, J., Luo, S., Zhu, D., Shao, Y., Li, Y., ... & Wu, C. (2022). Mining Latent Relationships among Clients: Peer-to-peer Federated Learning with Adaptive Neighbor Matching. arXiv preprint arXiv:2203.12285.
• Jia, X., Xiao, J., & Wu, C. (2022). TICS: text–image-based semantic CAPTCHA synthesis via multi-condition adversarial learning. The Visual Computer, 38(3), 963-975.
• Zhang, J., Zhang, L., Li, G., & Wu, C. (2022). Adversarial Examples for Good: Adversarial Examples Guided Imbalanced Learning. arXiv preprint arXiv:2201.12356.
• 何佳晋, 居豪, & 吴超. (2022). 中国 MSM 人群 HIV 新发感染率及其影响因素的 Meta 分析. 预防医学, 34(1), 70-77.
• Wang, P., Peng, D., Yu, S., Wu, C., Wang, X., Childs, P., ... & Li, L. (2022). Verifying Design Through Generative Visualization of Neural Activity. In Design Computing and Cognition’20 (pp. 555-573). Springer, Cham.
• He, J., Li, J., Jiang, S., Cheng, W., Jiang, J., Xu, Y., ... & Wu, C. (2022). Application of machine learning algorithms in predicting HIV infection among men who have sex with men: Model development and validation. Frontiers in public health, 10.
• Zhang, J., Li, B., Xu, J., Wu, S., Ding, S., Zhang, L., & Wu, C. (2022). Towards Efficient Data Free Black-Box Adversarial Attack. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15115-15125).
• Wu, C., Xu, C., Mao, F., Xu, X., & Zhang, C. (2022). The impact of invisible-spreaders on COVID-19 transmission and work resumption. Plos one, 17(1), e0252994.
• Zhang, F., Kuang, K., Liu, Y., Wu, C., Wu, F., Lu, J., ... & Xiao, J. (2021). Unified Group Fairness on Federated Learning. arXiv preprint arXiv:2111.04986.
• You, Z., Wu, X., Chen, K., Liu, X., & Wu, C. (2021, September). Evaluate the Contribution of Multiple Participants in Federated Learning. In International Conference on Database and Expert Systems Applications (pp. 189-194). Springer, Cham.
• Huang, Xiaojie, Jun Xiao, and Chao Wu. "Design of Deep Learning Model for Task-Evoked fMRI Data Classification." Computational Intelligence and Neuroscience 2021 (2021).
• Shuang Luo, Didi Zhu, Zexi Li, Chao Wu*. Ensemble Federated Adversarial Training with Non-IID data, FTL-IJCAI'21 Workshop.
• Zhang, H., Shen, T., Wu, F., Yin, M., Yang, H., & Wu, C. (2021). Federated Graph Learning--A Position Paper. arXiv preprint arXiv:2105.11099.
• Huang, H., Wang, Z., Zhang, J., He, Z., Wu, C., Xiao, J., & Alonso, G. (2021). Shuhai: A Tool for Benchmarking HighBandwidth Memory on FPGAs. IEEE Transactions on Computers.
• Jia, Xinkang, Jun Xiao, and Chao Wu. "TICS: text–image-based semantic CAPTCHA synthesis via multi-condition adversarial learning." The Visual Computer (2021): 1-13.
• Huang, G., Wu, C., Hu, Y., & Guo, C. (2021). Serverless Distributed Learning for Smart Grid Analytics. Chinese Physics B.
• Lee, C. H., He, Z., Li, Z., Lu, X., Wang, J., & Wu, C. (2021, February). A Comparison of Machine Learning Algorithms for Automatic Cloud Resource Scaling on a Multi-Tenant Platform. In Journal of Physics: Conference Series (Vol. 1828, No. 1, p. 012039). IOP Publishing.
• Chao Wu*, Yan Li, Junxiang Li, Qiongdan Zhang and Fei Wu, Web-based Platform for K-12 AI Education in China, Eleventh AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-21), 2020
• Pan Wang, Danlin Peng, Simiao Yu, Chao Wu, Peter Childs, Yike Guo and Ling Li, Verifying Design through Generative Visualisation of Brain Decoding from Neural Activities, NINTH INTERNATIONAL CONFERENCE ON DESIGN COMPUTING AND COGNITION, DCC'20.
• Chao Wu, Pei Zheng, Xinyuan Xu, Shuhan Chen, Nasi Wang, Simon Hu, Predicting urban mental state: a comparison of approaches, International Journal of Environmental Research and Public Health, 2020.17(21)
• Wu, Chao, Guolong Wang, Simon Hu, Yue Liu, Hong Mi, Ye Zhou, Yi-ke Guo, and Tongtong Song. "A data driven methodology for social science research with left-behind children as a case study." PloS one 15, no. 11 (2020).
• Chao Wu, Zhen Wang, Simon Hu, Julien Lépine, Xiaoxiang Na, Marc Stettler, Daniel Ainalis, MACHINE-LEARNING APPROACH FOR AUTOMATIC ROAD CONDITION MONITORING WITH SMARTPHONE SENSING DATA, 2020, Sensors.
• Conghai Zhang, Xinyao Xiao, Chao Wu, Medical Fraud and Abuse Detection System based on Machine Learning, International Journal of Environmental Research and Public Health, 17(19), 7265, 2020
• Qin, Fang-Yu, Zhe-Qi Lv, Dan-Ni Wang, Bo Hu, and Chao Wu. "Health status prediction for the elderly based on machine learning." Archives of Gerontology and Geriatrics (2020): 104121.
• Taleongpong Panukorn, Hu Simon, Jiang Zhoutong, Chao Wu, Popo-ola Sunday, Han Ke. “Machine Learning Techniques to Predict Reactionary Delays and Other Associated Key Performance Indicators on British Railway Network”, Journal of Intelligent Transportation System, 2020.
• Fang C H, SHAO Z Z, WU C,“A Low-Cost Method for Designing and Updating a DRGs Classifier Based on Machine Learning ", 2020, the 4th International Conference on Medical and Health Informatics (ICMHI 2020).
• D. Wu, T. Xiao, X. Liao, J. Luo, C. Wu, S. Zhang, Y. Li, Y. Guo, "When Sharing Economy Meets IoT: Towards Fine-grained Urban Air Quality Monitoring through Mobile Crowdsensing on Bike-share System", ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp), 2020.
• 郁建兴, 涂怡欣, and 吴超. "探索整合型医疗卫生服务体系的中国方案 — 基于安徽, 山西与浙江县域医共体的调查." 治理研究 1 (2020): 2 (新华文摘 2020-10).
• 吴超, and 郁建兴. "面向公共管理的数据所有权保护, 定价和分布式应用机制探讨." 电子政务 1 (2020): 6.
• Xue, Zeyue, Shuang Luo, Chao Wu, Pan Zhou, Kaigui Bian, and Wei Du. "Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach." arXiv preprint arXiv:2002.02202 (2020).

Teaching教学

• Data analysis and modelling for PA (including UPA)公共管理数据分析与建模（含UPA）: Course projects课程项目 (accessed within ZJU)（需在浙大校内访问）
• AI algorithm and system人工智能算法与系统
• Introduction to AI (Spring/Summer semester 2021)人工智能导论（2021春夏学期）
• Machine learning algorithms and platforms (for School of Software Engineering)机器学习算法与平台（软件学院）
• Smart Emergency Management智慧应急管理
• Short Course: Data Driven Social Analytics短期课程：数据驱动的社会分析

Projects项目

• Mo: Mo is a web-based platform for both AI modelling and eduction. In addition to the public version. It also has ZJU version, university version, higher vocational education version, high school version, and K-12 version.Mo 是一个面向人工智能建模和教育的在线平台。除公开版本外，还提供浙大版、高校版、高职版、高中版和K-12版。
• Distributed AI Platform分布式人工智能平台: This work has been funded by National Natural Science Foundation of China.该项目由国家自然科学基金资助。
• Intelligent Transportation智能交通: Some examples can be found here.部分案例可在此处查看。
• Social Simulation with Multi-Agent Reinforcement Learning基于多智能体强化学习的社会仿真

Vacancies招生招聘

Contact Information联系方式