I am a final-year PhD student at University of Illinois at Urbana-Champaign (UIUC). I am fortunate to be advised by Professor Jingrui He. Before that, I completed my bachlor degree in Computer Science at University of Science and Technology of China (USTC). My research interest mainly lies in trustworthy machine learning with a special focus on fairness, robustness and scalability. I am particularly interested in applying these principles to critical real-world applications including medicare, e-commerce, and social systems. I am also interested in understanding bias in foundation models.
📖 Educations
-
2020 - 2025 (expected), University of Illinois Urbana-Champaign
Ph.D. in Information Sciences, Advisor: Prof. Jingrui He
-
2016 - 2020, University of Science and Technology of China.
Bachelor of Computer Science, Advisor: Prof. Xiangyang Li and Prof. Xiangnan He
📝 Publications
Preprint
-
Fair Anomaly Detection For Imbalanced Groups
Ziwei Wu*, Lecheng Zheng*, Yuancheng Yu, Ruizhong Qiu, John Birge, Jingrui He
preprint 2024.
-
Preference-aware Gradient Matching for Fairness
Ziwei Wu, Yikun Ban, Jingrui He
preprint 2024.
-
Rethinking Fairness in LLM Tabular Tasks: A Mixture of LoRA Experts Approach
Ziwei Wu, Yiwei Cai, Rashid Islam
preprint 2024.
-
Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
Zihao Li, Xiao Lin, Zhining Liu, Jiaru Zou, Ziwei Wu, Lecheng Zheng, Dongqi Fu, Yada Zhu, Hendrik Hamann, Hanghang Tong, Jingrui He
preprint 2024.
Conference
-
Neural Active Learning Beyond Bandits.
Yikun Ban, Ishika Agarwal, Ziwei Wu, Yada Zhu, Kommy Weldemariam, Hanghang Tong, Jingrui He
-
Training Fair Deep Neural Networks by Balancing Influence.
Haonan Wang*, Ziwei Wu\*, Jingrui He
-
Deep Active Learning by Leveraging Training Dynamics.
Haonan Wang, Wei Huang, Ziwei Wu, Andrew Margenot, Hanghang Tong, Jingrui He., Jingrui He
-
Fairness-aware Model-agnostic Positive and Unlabeled Learning. Distinguished Paper Award
Ziwei Wu, Jingrui He
-
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System. Most Influential KDD Papers
Tianxin Wei, Fuli Feng, Jiawei Chen, Ziwei Wu, Jinfeng Yi, Xiangnan He
-
Fast Adaptation for Cold-start Collaborative Filtering with Meta-learning.
Tianxin Wei, Ziwei Wu, Ruirui Li, Ziniu Hu, Fuli Feng, Xiangnan He, Yizhou Sun, Wei Wang.
🎖 Honors and Awards
- Distinguished Paper Award of FAccT, 2022
- Best Program Committee of CIKM, 2022
- Most Influential KDD Papers, 2021
- Valedictorian of Class of 2020 of USTC, 2020
- Guo Moruo Scholarship (Summa Cum Laude), 2019
- Tang Lixin Scholarship, 2018
- National Scholarship of China, 2017