周昉

2022 - 至今，华东师范大学，副教授，博士生导师

2018 - 2022，华东师范大学，副研究员

2015 - 2018，美国天普大学，Postdoc；

2013 - 2014，英国诺丁汉大学宁波分校，Research fellow；

本人专注于人工智能、机器学习与数据挖掘领域，致力于为复杂、开放世界场景设计具有高鲁棒的算法模型。

• 开放环境机器学习：开放集识别 (Open-set Recognition)，领域泛化 (Domain Generalization)，持续学习 (Continual Learning) 与少样本学习 (Few-shot Learning);

• 前沿模型与表征学习：基础大模型 (Foundation Models) 和表格学习 (Tabular Learning);

• 关键产业交叉应用：以解决真实应用问题为导向，驱动前沿AI技术在金融科技、数智能源、工业人工智能等领域的落地与创新。

开设课程

1. 数据挖掘（本科选修课）

2. 专业英语（本科必修课）

纵向研究课题

1. 面向多源多视图数据的结构化预测模型研究 （国自然-青基）

2. 面向区块链数据的内容管控技术研究 （上海市科技创新行动计划）

3. 面向异构长尾表格数据的广义异常识别（国自然-面上项目）

校企合作项目

1. 收钱吧商户贷款及交易行为预测

2. 收钱吧商户交易行为异常检测

3. 上海银行内部账号资金异动智能检测

4. 上海三峡研究院可研报告自动编制研究

详细信息请见个人主页： https://sites.google.com/view/fangzhou

代表论文：

16. Ji L., Dong C., Pavlovski M., Wang Y., Zhou F.*, "EdgeBoost4PAD: An Adaptive Strategy for Enhancing Semi-Supervised Priority-Aware Anomaly Detection", IEEE Transactions on Knowledge and Data Engineering (TKDE), 2026.

15. Zhang Y., Shou H., Lu G., Zhou F.*, "VISRA: Vision-Language Induced Supervision and Representation Alignment for Long-Tailed Generalized Category Discover", Proc. 35th Int’l Conf. on Information and Knowledge Management (CIKM), 2026.

14. Lu G. Zhou F.*, Jin C., "Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors", Proc. 19th European Conference on Computer Vision (ECCV'26), 2026.

13. Lu G., Zhou F.*, Shou H., Pavlovski M., Dong C., Liao B., Jin C., “Normal Invariant Representation Learning via Weight-guided Distribution Alignment for Open-set Anomaly Detection”, DASFAA, pp. 641-657, 2026.

12. Zhou F., Chen Z., Pavlovski M., Zhang Y., "ReLKD: Inter-Class Relation Learning with Knowledge Distillation for Generalized Category Discovery", Proc. 28th European Conference on Artificial Intelligence (ECAI'25), 2025.

11. Shou H., Lu G., Pavlovski M., Zhou F.^*, “READ: Robust and Efficient Anomaly Detection under Data Contamination and Limited Supervision”, Proc. 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD ’25), 2025.

10. Wei R., He Z., Pavlovski M., Zhou F.*,  “GAD: A Generalized Framework for Anomaly Detection at Different Risk Levels”, Proc. 33^rd Int’l Conf. on Information and Knowledge Management (CIKM), 2024.

9. Miao Y., Zhou F.*,  Pavlovski M., Qian W., “Learning Legal Text Representations via Disentangling Elements”, Expert Systems With Applications, 2024. 

8. Lu G., Zhou F.*, Pavlovski M., Zhou C., Jin C., “A Robust Prioritized Anomaly Detection when Not All Anomalies are of Primary Interest”, Proc. 40th International Conference on Data Engineering (ICDE), 2024.

7. Miao Y., Pavlovski M., Chen Z., Zhou F.*, “Multi-Aspect Matching between Disentangled Representations of User Interests and Content for News Recommendation”， Proc. 29^th Int’l Conf. on Database Systems for Advanced Applications (DASFAA), 2024.

6. Zhou F.*, Gao S., Ni L., Pavlovski M., Dong Q., Obradovic Z., Qian W., “Dynamic Self-paced Sampling Ensemble for Highly Imbalanced and Class-overlapped Data Classification,” Data Mining and Knowledge Discovery. 2022 

5. Roychoudhury, S. Zhou, F.*, Obradovic, Z., “Leveraging Dependencies among Learned Temporal Subsequences,” Proc. 22nd SIAM Int’l Conf. Data Mining (SDM 2022), Alexandria, VA, May 2022. 

4. Zong W., Zhou F.*, Pavlovski M., Qian W., “Peripheral Instance Augmentation for End-to-End Anomaly Detection using Weighted Adversarial Learning”, Proc. 27th Int’l Conf. on Database Systems for Advanced Applications (DASFAA), April 2022. 

3. Li X., Pavlovski M., Zhou F.*, Dong Q., Qian W., Obradovic Z., “Supervised Multi-view Latent Space Learning by Jointly Preserving Similarities across Views and Samples,” Proc. 27th Int’l Conf. on Database Systems for Advanced Applications (DASFAA), April 2022. 

2. Roychoudhury S.*, Zhou F.*, Obradovic Z.,  Leveraging Subsequence-orders for Univariate and Multivariate Time-series Classification, Proc. 19th SIAM Int’l Conf. Data Mining(SDM), Calgary, Canada, May 2019.

1. Pavlovski M., Zhou F., Arsov N., Kocarev L., Obradovic Z., “Generalization-Aware Structured Regression towards Balancing Bias and Variance”, Proc. 27th International Joint Conference on Artificial Intelligence (IJCAI), 2018, pp. 2616-2622.