Welcome to Fang ZHOU's homepage

Bio

Fang Zhou currently is an Associate Professor at Data Science and Engineering, East China Normal University. She obtained her Ph.D. degree at the University of Helsinki in 2012, under the supervision of Prof. Hannu Toivonen. From 2013-2015, She worked as a research scientist at the University of Nottingham Ningbo China. From 2015-2018, She worked as a postdoctoral researcher under the supervision of Prof. Zoran Obradovic at Temple University. 

Research Interests

My research focuses on artificial intelligence and data mining, specifically designing robust algorithms for complex, open-world environments. My key technical areas include open-set recognition, out-of-distribution generalization, continual learning, and few-shot learning. I also explore foundation models and tabular learning. My goal is to drive innovative solutions for critical, real-world challenges in FinTech, digital energy, and industrial AI.

Selected Publications ( see full list in Google scholar )

• Lu G., Zhou F.*, Jin C., "Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors", ECCV, 2026.

• 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. (Paper, Code)  

• Shou H., Lu G., Pavlovski M., Zhou F.*, "READ: Robust and Efficient Anomaly Detection under Data Contamination and Limited Supervision", KDD, pp.2586-1596, 2025. (Paper, Code) 

• Zhou F.*, Chen Z., Pavlovski M., Zhang Y., "ReLKD: Inter-Class Relation Learning with Knowledge Distillation for Generalized Category Discovery", ECAI, pp.3122-3129, 2025. (Paper, Code)

• Wei R., He Z., Pavlovski M., Zhou F.*,  “GAD: A Generalized Framework for Anomaly Detection at Different Risk Levels”, CIKM, pp.2513-2522, 2024. (Paper, Code)  

• Lu G., Zhou F.*, Pavlovski M., Zhou C., Jin C., “A Robust Prioritized Anomaly Detection when Not All Anomalies are of Primary Interest”, ICDE, pp.775-788, 2024. (Paper, Code)

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

• 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. (Paper, Code )

• 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, pp.504-512. (Paper) 

• 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-2022), April 2022, pp.506-522. (Paper, Code)  

• Zhou, F., Gillespie, A., Gligorijevic, Dj., Gligorijevic, J., Obradovic, Z. (2020) “Use of Disease Embedding Technique to Predict the Risk of Progression to End-Stage Renal Disease,” Journal of Biomedical Informatics, vol. 105, 103409, 2020. (Paper) 

• 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. (Paper) 

• 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. (Paper) 

• Zhou F., Qu Q., Toivonen H., “Summarisation of Weighted Networks”, Journal of Experimental & Theoretical Artificial Intelligence, 2017, 29(5): 1023-1054. 

• Vujicic, T., Glass, J., Zhou, F., Obradovic, Z. “Gaussian Conditional Random Fields Extended for Directed Graphs,” Machine Learning. 2017, 106(9-10): 1271-1288. (Paper) 

• Pavlovski M., Zhou F., Stojkovic I., Kocarev L., Obradovic Z., “Adaptive Skip-Train Structured Regression for Temporal Networks”, ECML-PKDD 2017, pp 305-321. (Paper) 

We are seeking highly motivated, positive, and enthusiastic students to join our team. 

If you are interested in our research topics, please contact me through email.