Xi-Zhu Wu @ LAMDA

Modified: 2014/08/25 22:19 by admin - Uncategorized
Image Chinese name
Xi-Zhu Wu (X.-Z. Wu)

PhD Candidate
Department of Computer Science
National Key Laboratory for Novel Software Technology
Nanjing University

email: wuxz # lamda.nju.edu.cn (gmail account "wuxz.gm")

Currently I am a final year PhD student of Department of Computer Science and Technology in Nanjing University and a member of LAMDA Group (LAMDA Publications), led by Professor Zhi-Hua Zhou.

I defended my PhD dissertation at 2020-08-24. I will work as a data scientist at Optiver Shanghai, which is a proprietary trading firm and market maker.



Professor Zhi-Hua Zhou.


2010 - 2014    B.Sc. degree in Computer Science in Kuangyaming Honor School of Nanjing University
2014 - 2016    M.Sc. candidate in LAMDA Group, Nanjing University, supervised by Prof. Zhi-Hua Zhou
2016 - now     Ph.D. candidate in LAMDA Group, Nanjing University, supervised by Prof. Zhi-Hua Zhou

Visited Song Liu in University of Bristol (Feb-May) in 2019. A wonderful journey in Britain!

Research Interest

I am interested in machine learning. Currently I am focusing on the subfields:
  • Model Reuse : Towards helping target task by reusing source models without source data. It is a topic in learnware.
  • Multi-Label Learning : Learning from objects with multiple labels.

Besides, I have a good sense of measuring learning models.


  • Xi-Zhu Wu, Wenkai Xu, Song Liu, Zhi-Hua Zhou. Model Reuse with Reduced Kernel Mean Embedding Specification. [arXiv]


  • Tian-Zuo Wang, Xi-Zhu Wu, Sheng-Jun Huang and Zhi-Hua Zhou. Cost-effectively Identifying Causal Effects When Only Response Variable is Observable. To appear in the 37th International Conference on Machine Learning (ICML'20).
  • Liang Yang, Xi-Zhu Wu, Yuan Jiang and Zhi-Hua Zhou. Multi-Label Learning with Deep Forest. In: Proceedings of the 24th European Conference on Artificial Intelligence (ECAI'20), Santiago de Compostela, Spain, 2020. To appear. [arXiv][Code]
  • Xi-Zhu Wu, Song Liu and Zhi-Hua Zhou. Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin. In: Proceedings of the 36th International Conference on Machine Learning (ICML'19), Long Beach, CA, 2019.[PDF][Supplementary PDF][Slides][Poster@ICML][A Better Poster@MLA][Code]
  • Xi-Zhu Wu and Zhi-Hua Zhou. A Unified View of Multi-Label Performance Measures. In: Proceedings of the 34th International Conference on Machine Learning (ICML'17), Sydney, Australia, 2017. [PDF] [Supplementary PDF][Slides][Poster][Code]
  • Xi-Zhu Wu and Zhi-Hua Zhou. Model Reuse with Domain Knowledge. SCIENTIA SINICA Informationis, 2017.[PDF]
    (CCML best paper award, In Chinese: 领域知识指导的模型重用. 中国科学: 信息科学)

My google scholar.

Awards & Honors

  • First-Class Graduate Student Scholarship. 2018
  • Huawei Scholarship. 2017
  • First-Class Graduate Student Scholarship. 2017
  • ICML Student Travel Award. 2017
  • CCML Best Paper Award. 2017
  • The Second Prize in CCF Big Data Competition. 2014
  • Microsoft Youngfellow Scholarship. 2013
  • Excellent Project Completion in the Undergraduate Innovation Program. 2013
  • Elite Project Scholarship. 2013
  • Elite Project Scholarship. 2012

Academic Service

  • Reviewer for journals: IEEE TPAMI, IEEE TKDE, Machine Learning
  • Conference senior PC member: ECAI'20
  • Reviewer for conferences: NeurIPS'20, ICML'20, AAAI'20, NeurIPS'19, ICML'19, ACML'19, AAAI'19, NIPS'18 (rated top 30% reviewer), ACML'18, PRICAI'18, CCML'17.

Teaching Assistant

National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(In Chinese:) 南京市栖霞区仙林大道163号,南京大学仙林校区603信箱,软件新技术国家重点实验室,210023。

Last modified: 2020-09-06