Weizhu QIAN

Assistant Professor at Soochow University, China

Contact: qian(dot)weizhu123(at)gmail(dot)com

Research Interests

Deep Learning, Probabilistic Inference, Generative Model, Optimal Transport, Time Series, Uncertainty Quantification

Selected Publications 

• Weizhu Qian, Dalin Zhang, Yan Zhao, and Yunyao Cheng. "Conditional Lagrangian Wasserstein Flow for Time Series Imputation." arXiv preprint arXiv:2410.07550 (2024). [paper]

• Weizhu Qian, Yan Zhao, Dalin Zhang, Bowei Chen, Kai Zheng, Xiaofang Zhou. Towards A Unified Understanding of Uncertainty Quantification in Traffic Flow Forecasting. (IEEE Transactions on Knowledge and Data Engineering, 2024, 36(5), pp. 2239-2256).[paper][code][slide]

• Weizhu Qian, Dalin Zhang, Yan Zhao, Kai Zheng, James J.Q. Yu. Uncertainty Quantification for Traffic Forecasting: A Unified Approach (39th IEEE International Conference on Data Engineering, ICDE, pp. 992-1004, 2023).

• Weizhu Qian, Thomas Dyhre Nielsen, Yan Zhao, Kim Guldstrand Larsen, James J.Q. Yu. Uncertainty-Aware Temporal Graph Convolutional Network for Traffic Forecasting. (IEEE Transactions on Intelligent Transportation Systems, 2024, 25(05) pp. 8578-8590).

• Weizhu Qian, Fabrice Lauri, Franck Gechter. Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems. (Neurocomputing, 2021, 435, pp.228-238).

Reviewer

Neurips, ICLR, AISTATS, ICML, AAAI, CIKM, TKDE, TITS, etc.

Teaching

• Introduction to Artificial Intelligence (Spring 2025)

• Machine Learning (Fall 2024)

• Comprehensive Practice Project (Applied Data Science with Python Specialization, Fall 2023 and 2024)

Languages

• English: Advanced

• French: Intermediate

• Chinese: Native

Miscellaneous

• Reading Materials

• Monte Carlo Method