张伟嘉

发布者:张伟嘉发布时间:2021-10-25浏览次数:218


Weijia Zhang (张伟嘉)

    Ph.D., Associate Professor, Google Scholar

    zhangwj [at] seu.edu.cn

    School of Computer Science and Engineering, Southeast University

    Room 146, School of Computer Science and Engineering, Southeast University Jiulonghu Campus, Nanjing, China.

    Member of the PAttern Learning and Mining (PALM) Lab.



Brief Biography

I am currently an associate professor with the school of Computer Science and Engineering, Southeast University, China. Before joining SEU, I was a research fellow for three years at the University of South Australia. I received my Ph.D. degree from the school of Information Technology and Mathematical Science, University of South Australia, in 2018 and the M.Sc. degree from the department of Computer Science and Technology, Nanjing University, in 2014. My undergraduate study was also completed at Nanjing University, in the department of Mathematics.


本科毕业于南京大学数学系,在听取了张高飞老师关于如何选择数学专业的建议后选择了计算数学专业,从而得以顺利毕业。研究生毕业于南京大学计算机科学与技术系,因为觉得教机器来学习的概念听起来很酷,有幸在周志华老师的指导下学习和研究机器学习。博士毕业于澳大利亚南澳大学,因为那里的动物看起来傻萌又可爱,在Jiuyong Li老师的指导下学习和研究因果推断。


人生是一个不断学习和探索新事物,并对过往的理解和经历进行审视的过程。如果你对探索新事物有兴趣,欢迎报考我的研究生。作为导师,我承诺以自己最大的努力来指导和帮助学生。但是,也请务必注意,学术研究和人生一样,不一定会一帆风顺,但不断努力和尝试一定会带来进步。著名绝地大师,Master Yoda曾经说过:The greatest teacher, failure is.


Research Interests

Causal Inference - Causal Effect Estimation, Causal Structure Learning

Machine Learning - Weakly Supervised Learning, Causality-based Learning

Applications - Solving problems in Data-Driven Decision Making, Medical Diagnosis, Bioinformatics, Automobile, and Mining Industries.


因果推断 - 因果效应估计,因果结构学习

机器学习 - 弱监督学习,基于因果的机器学习

应用 使用机器学习和因果推断来解决基于数据的决策,医学诊断,生物信息学等行业中的应用问题。


Selected Publications

1. Zhang, W., Li, J., Liu, L., A unified survey of uplift modeling and treatment effect heterogeneity modeling. ACM Computing Surveys (CSUR), 2021, 54(8):162. 

2. Zhang, W., Non-i.i.d. multi-instance learning for predicting instance and bag labels using variational autoencoder. The 30th International Joint Conference on Artificial Intelligence (IJCAI), 2021, 3377-3383. 

3. Li, J., Zhang, W., Liu, L., Yu, K., Le, T., Liu, J., A general framework for causal classification. International Journal of Data Science and Analytics (JDSA), 2021, 11(2):127-139. 

4. Zhang, W., Lin, L., Li, J., Treatment effect estimation with disentangled latent factors. The 30th International Joint Conference on Artificial Intelligence (AAAI), 2021, 10923-10930. 

5. Zhang, W., Lin, L., Li, J., Robust multi-instance learning with stable instances. The 24th European Conference on Artificial Intelligence (ECAI), 2020, 1682-1689. 

6. Tomasoni, M., Gomez, S., Crawford, J., Zhang, W., Choobdar, S., Marbach, D., Bergmann, S., MONET: a toolbox integrating top-performing methods for network modularization. Bioinformatics, 2020, 36(12): 3920-3921. 

7. Zhang, W., Lin, L., Li, J., Estimating heterogeneous treatment effects by balancing heterogeneity and fitness. BMC Bioinformatics, 2018, 19(19): 518. 

8. Zhang, W., Le, T., Lin, L., Zhou, Z.-H., Li, J., Mining heterogeneous causal effects for personalized cancer treatment. Bioinformatics, 2017, 33(15): 2372-2378. 

9. Zhang, W., Zhou, Z.-H., Multi-instance learning with distribution change. The 28th AAAI Conference on Artificial Intelligence (AAAI), 2014, 2184-2190. 

10. Choobdar, S. et al., (Zhang, W.  as a consortium author), Assessment of network module identification across complex diseases. Nature Methods, 2020, 16(9): 843-852. 

For more information, please visit my personal homepage!