I’m a third-year Ph.D. student at the Department of Computing, the Hong Kong Polytechnic University, supervised by Dr. Wu Xiao-Ming. I obtained my B.S. degree from the College of Computer Science and Technology, Zhejiang University. My main area of interest is machine learning, both theoretical and practical.
Current Interests and Projects:
- Machine Learning
- Semi-supervised Learning
- Unsupervised Learning
- Learning from Graph-Structured Data
- Graph Signal Processing
- Graph Convolution
- Graph Sampling
“Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification.”
Guangfeng Yan, Lu Fan, Qimai Li (co-first author), Han Liu, Xiaotong Zhang, Xiao-Ming Wu, Albert Y.S. Lam.
In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (Long Paper). 2020. [ACL-20] [PDF]
“Reconstructing Capsule Networks for Zero-shot Intent Classification.”
Han Liu, Xiaotong Zhang, Lu Fan, Xuandi Fu, Qimai Li, Xiao-Ming Wu, Albert Y.S. Lam.
In Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing (Long Paper). 2019. [EMNLP-19] [PDF]
[Publication] “Attributed Graph Clustering via Adaptive Graph Convolution.”
Zhang, Xiaotong*, Han Liu*, Qimai Li (co-first author), Xiao-Ming Wu.
In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019. [IJCAI-19] [PDF] [CODE] [PPT]
[Publication] “Label Efficient Semi-Supervised Learning via Graph Filtering.”
Li, Qimai, Xiao-Ming Wu, Han Liu, Xiaotong Zhang, and Zhichao Guan.
In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019. [CVPR-19] [PDF] [CODE] [PPT] [POSTER]
[Award] I am awarded Hong Kong Ph.D. Fellowship by the Research Grants Council of Hong Kong.
250 out of 14,000+ candidates, 1.7% acceptance rate.
[Publication] “Deeper insights into graph convolutional networks for semi-supervised learning.”
Li, Qimai, Zhichao Han, and Xiao-Ming Wu.
In Thirty-Second AAAI Conference on Artificial Intelligence. 2018. [AAAI-18 Oral] [PDF] [CODE] [BLOG] [PPT]