Hey, I am Yifan Chen, an Assistant Professor in Computer Science and Mathematics (affiliate) at Hong Kong Baptist University.

I obtained my Ph.D. degree from Department of Statistics, University of Illinois Urbana-Champaign in 2023, advised by Prof. Yun Yang. I fortunately work with Prof. Yun Yang, Prof. Ruoqing Zhu, Prof. Heng Ji, and Prof. Jingrui He during my Ph.D. studies. I also collaborated with Dilek Hakkani-Tur at Amazon Alexa AI, and Jie Chen at IBM Research. Before that, I received my B.S. degree in Statistics from Fudan University in 2018, advised by Prof. Juan Shen and Prof. Chenghong Zhang.

💻 Research

I am broadly interested in the general area of efficient machine learning, aiming to understand the statistical structures of modern machine learning algorithms and apply these insights to real-world computational challenges. I especially focus on non-parametric models and neural networks with intensive matrix operations, such as Transformers (language models) and graph neural networks (GNNs).

🔥 News

• 2023.09:  🎉🎉 One paper was accepted to NeurIPS 2023! Congratulations to Xiaoyuan and other collaborators from Prof. Qingfu Zhang’s group at CityU!
• 2023.07: I am looking for self-motivated (visiting) Ph.D. students / (remote) research assistants to work with me on machine learning. Fellowships / salaries are provided to qualified candidates. Any interested applicants can directly send me your CV and a brief introduction to your research interest to “ychen.stat.ML@outlook.com”. Please refer to the Zhihu post for more details.
• 2023.04:  🎉🎉 I will join CS @ Hong Kong Baptist University as an assistant professor in Fall 2023.
• 2023.04:  🎉🎉 Two papers were accepted to ICML 2023!

📝 Publications

* Co-first author, ✉️ Corresponding author

• NeurIPS 2023 Hypervolume Maximization: A Geometric View of Pareto Set Learning
  Xiaoyuan Zhang, Bo Xue, Xi Lin, Yifan Chen✉️, Qingfu Zhang✉️
• ICML 2023 A Gromov–Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
  Yifan Chen, Rentian Yao, Yun Yang, Jie Chen
• ICML 2023 NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning
  Tianxin Wei*, Zeming Guo*, Yifan Chen*✉️, Jingrui He✉️
• TMLR Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
  Yifan Chen*, Tianning Xu*, Dilek Hakkani-Tur, Di Jin, Yun Yang, Ruoqing Zhu. Transactions on Machine Learning Research (TMLR), 2023.
• EMNLP 2022 (Oral) Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
  Yifan Chen*, Devamanyu Hazarika*, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur
• NAACL 2022 (Oral) Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
  Yifan Chen*, Qi Zeng*, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang
• NAACL 2022 (Findings) Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
  Yifan Chen*, Devamanyu Hazarika*, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur
• NeurIPS 2021 Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr"om Method
  Yifan Chen*, Qi Zeng*, Heng Ji, Yun Yang
• AISTATS 2021 Accumulations of Projections—A Unified Framework for Random Sketches in Kernel Ridge Regression
  Yifan Chen, Yun Yang
• AISTATS 2021 Fast Statistical Leverage Score Approximation in Kernel Ridge Regression
  Yifan Chen, Yun Yang

🎖 Honors and Awards

• 2023.05 Dissertation Completion Fellowships (gratefully declined due to early graduation), USD $25,000, University of Illinois Graduate College
• 2023.05 The Fortieth International Conference on Machine Learning (ICML 2023) Grant Award, USD $1,500
• 2018.06 Shanghai Outstanding Graduate, Shanghai Municipal Education Commission

💬 Professional Talks

• 2023.08, A Gromov–Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening, HKBU Math department invited talk, Hong Kong
• 2023.08, NTK-approximating MLP Fusion for Efficient Language Model Fine-tuning, the 1st International Conference on AI-generated Content (AIGC2023) invited talk, Remote
• 2022.08, One Expert with Multiple Instruments, Microsoft Azure internal talk, Remote
• 2022.08, Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences, AI Time PhD NAACL Special Session, Remote
• 2021.12, Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention, Amazon Alexa AI internal talk, Sunnyvale, CA, USA