I’m the second year PhD student at the State Key Laboratory of Pattern Recognition, the University of Chinese Academy of Sciences, advised by Prof. Tieniu Tan. I have also spent time at Microsoft, advised by Prof. Jingdong Wang, alibaba DAMO Academy, work with Prof. Rong Jin. I strongly believe in the power of interdisciplinary collaboration and the potential it holds for driving impactful research outcomes. If you are interested in partnering on research projects, offering internship opportunities or exchange programs, I would be thrilled to connect with you.
My research interest lies in the development of robust and reliable machine learning (ML) systems that can effectively handle unexpected inputs and distribution shifts. While conventional software systems are expected to provide warnings for unexpected inputs, ML systems often fail silently due to their strong dependence on specific input properties, such as the assumption of independent and identically distributed (i.i.d.) data. In light of this challenge, my research aims to address three critical objectives.
- Firstly, I seek to develop innovative techniques to detect and identify distribution shifts in ML systems. This involves exploring statistical and machine learning methods that can effectively capture changes in data distributions and trigger appropriate responses.
- Secondly, I am interested in developing methods that can dynamically adapt and correct classifiers on the fly, responding to distribution shifts in real-time when possible, this involves investigating approaches such as online learning, active learning, and adaptive algorithms that can update models and decision boundaries based on evolving data distributions.
- Ultimately, my work aims to contribute to the development of foundational principles for building ML systems that can be relied upon in real-world scenarios, providing practical guidance for implementing robust and dependable ML systems.
- 2023.05 🎉🎉 Domain-Specific Risk Minimization for Out-of-Distribution Generalization has been accepted by SIGKDD 2023. [Code][Reading Notes]
- 2023.05 🎉🎉 AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation has been accepted by ICML 2023. [Code] [Reading Notes]
- 2023.01 🎉🎉 Free Lunch for Domain Adversarial Training: Environment Label Smoothing has been accepted by ICLR 2023. [Code] [Reading Notes]
- 2023.01 🎉🎉 Learning Domain Invariant Representations for Generalizable Person Re-Identification has been accepted by IEEE Transactions on Image Processing (T-IP).
- 2022.11 🎉🎉 Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation has been accepted by NeurIPS ML Safety workshop. [Code]
- 2022.04 🎉🎉 Towards Principled Disentanglement for Domain Generalization has been selected for an CVPR Oral presentation. [Reading Notes] [Code]
Domain-Specific Risk Minimization for Out-of-Distribution Generalization | SIGKDD, 2023 | [Code] |
Yi-Fan Zhang, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, Dacheng Tao, Xing Xie
Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Yi-Fan Zhang, xue wang, Jian Liang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan
Towards Principled Disentanglement for Domain Generalization | CVPR 2022 Oral | Code
Hanlin Zhang*, Yi-Fan Zhang*, Weiyang Liu, Adrian Weller, Bernhard Schölkopf, Eric P. Xing
Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation | NeurIPS ML Safety Workshop, 2022 | Code
Yi-Fan Zhang*, Hanlin Zhang*, Zachary Lipton, Li Erran Li, Eric Xing
Yi-Fan Zhang; Zhang Zhang; Da Li; Zhen Jia; Liang Wang; Tieniu Tann
Focal and efficient IOU loss for accurate bounding box regression | Neurocomputing, 2022 |
Yi-Fan Zhang, Weiqiang Ren, Zhang Zhang, Zhen Jia, Liang Wang, Tieniu Tan
(* denotes equal contribution.)
💻 Conference: PC Member/Reviewer for: ICML (2022,2023), NeurIPS (2022,2023), ECCV (2022), AAAI (2023,2024), CVPR (2022,2023), ICCV (2023), ICLR (2023,2024), EMNLP (2023)
💻 Workshops: PC Member for: MILETS@PAKDD’23, DMLR@ICML’23
🎖 Selected Awards
- Top Ten Best Student Models of South China University of Technology (Summa Cum Laude), 2020
- Jingtang He Technology Innovation Scholarship (Top 1‰, 5 out of 10000+ in university), 2020
- Contemporary Undergraduate Mathematical Contest in Modeling(CUMCM), National first prize (Top 1% globally), 2019.
📖 Work experience
- May 2022 - Now: Research Assistant on Alibaba DAMO.
- March 2021 - July: Research Assistant on Microsoft Research Asia.