Junwei Deng
PhD, Information Sciences, Illinois (in progress)
MS, Information, University of Michigan
B.Eng., Electrical and Computer Engineering, Shanghai Jiao Tong University
Pronouns: he/him
Research focus
I am interested in data-centric AI (e.g., data attribution), trustworthy machine learning (e.g., robustness, fairness), responsible AI (e.g., copyright issue for generative AI), and AI toolkit development.
Field Exam Area: Data attribution in modern AI models: methods and applications
Honors and Awards
- Shanghai Outstanding College Graduate (2020)
- National Scholarship (2018), the highest award provided by Ministry of Education in P.R. China.
Advisor
Publications & Papers
Deng, J., Li, T. W., Zhang, S., Liu, S., Pan, Y., Huang, H., ... & Ma, J. W. (2024). dattri: A Library for Efficient Data Attribution. Advances in Neural Information Processing Systems, 37.
Dai, J. J., Ding, D., Shi, D., Huang, S., Wang, J., Qiu, X., ... Deng, J. & Song, G. (2022). Bigdl 2.0: Seamless scaling of ai pipelines from laptops to distributed cluster. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 21439-21446).
Ma, J., Deng, J., & Mei, Q. (February 2022). Adversarial attack on graph neural networks as an influence maximization problem. In Proceedings of the fifteenth ACM international conference on web search and data mining (pp. 675-685).
Ma, J., Deng, J., & Mei, Q. (2021). Subgroup generalization and fairness of graph neural networks. Advances in Neural Information Processing Systems, 34, 1048-1061.