Fangchen Yu is currently a Ph.D. candidate in Computer and Information Engineering at The Chinese University of Hong Kong, Shenzhen (CUHK-SZ), under the supervision of Prof. Wenye Li and Prof. Jianfeng Mao. He obtained his Bachelor’s degree in Physics from the University of Chinese Academy of Sciences (UCAS) in 2020. His research interests focus on statistical learning, machine learning, and metric learning.

Research Interests

Optimization, Unsupervised Learning, Incomplete Data, Computer Vision, AI for Science.

Research Topics

• Efficient Optimization Algorithms for Incomplete Data (Previous Work)
  • Optimization of similarity and distance matrices for offline/online incomplete data
  • Estimation of inner product matrix for incomplete data on similarity search tasks
• Optimization and Generalization for Wasserstein Distance (Ongoing Work)
  • Fast and accurate tree Wasserstein distance for approximating 1-Wassserstein distance
  • Robust Wasserstein distance for unbalanced distributions
• Optimization for Visual Generative Models & AI for Science (Future Work)
  • Optimization for Wasserstein-based generative models (e.g., Point Cloud Completion)
  • New neural network design for the discovery of physical laws (e.g., K-A Networks)

Publications

• FedLF: Layer-wise Fair Federated Learning
  Zibin Pan, Chi Li, Fangchen Yu, Shuyi Wang, Haijin Wang, Xiaoying Tang, Junhua Zhao
  AAAI-2024: [Paper] [Code] [Poster] [bibtex]

• DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction
  Fangchen Yu (internship), Yina Xie, Lei Wu, Yafei Wen, Guozhi Wang, Shuai Ren, Xiaoxin Chen, Jianfeng Mao, Wenye Li
  WACV-2024: [Paper] [Code] [Poster] [bibtex]

• Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning
  Fangchen Yu, Runze Zhao, Zhan Shi, Yiwen Lu, Jicong Fan, Yicheng Zeng, Jianfeng Mao, Wenye Li
  NeurIPS-2023: [Paper] [Code] [Video] [PPT] [Poster] [bibtex]
• Online Estimation of Similarity Matrices with Incomplete Data
  Fangchen Yu, Yicheng Zeng, Jianfeng Mao, Wenye Li
  UAI-2023: [Paper] [Code] [Poster] [bibtex]
• Highly-Efficient Robinson-Foulds Distance Estimation with Matrix Correction
  Fangchen Yu, Rui Bao, Jianfeng Mao, Wenye Li
  ECAI-2023: [Paper] [Code] [Poster] [bibtex]
• From Incompleteness to Unity: A Framework for Multi-view Clustering with Missing Values
  Fangchen Yu, Zhan Shi, Yuqi Ma, Jianfeng Mao, Wenye Li
  ICONIP-2023 (Oral): [Paper] [bibtex]

• Metric Nearness Made Practical
  Wenye Li, Fangchen Yu, Zichen Ma
  AAAI-2023: [Paper] [Code] [Poster] [bibtex]

• Calibrating Distance Metrics Under Uncertainty
  Wenye Li, Fangchen Yu
  ECML-2022: [Paper] [bibtex]

• Learning Sparse Binary Code for Maximum Inner Product Search
  Changyi Ma, Fangchen Yu, Yueyao Yu, Wenye Li
  CIKM-2021 (Best Short Paper Finalist): [Paper] [bibtex]

Educations

• Sep. 2020 - Now,
  Ph.D. Candidate in Computer and Information Engineering, at The Chinese University of Hong Kong, Shenzhen (CUHK-SZ).
  
• Sep. 2016 - Jun. 2020,
  B.S. in Physics, at University of Chinese Academy of Sciences (UCAS).
  
• Aug. 2019 - Dec. 2019,
  Global Study Program, at University of California, Davis (UCD).

Professional Experience

• Jul. 2023 - Jun. 2024,
  Graduate Research Assistant, at Shenzhen Research Institute of Big Data, Shenzhen, China. (Supervisor: Dr. Yicheng Zeng)
  
• Mar. 2023 - Jul. 2023,
  Research Intern, at Vivo AI Lab, Shenzhen, China. (Area: Visual Understanding and Generation)

Honors and Awards

• 2020-2024: PhD Fellowship (Silver Class) at Shenzhen Research Institute of Big Data (SRIBD)
• Oct 2022: Class I Outstanding TA Award at Chinese University of Hong Kong, Shenzhen (CUHK-SZ)
• Jul 2021: Class II Outstanding TA Award at Chinese University of Hong Kong, Shenzhen (CUHK-SZ)
• Nov 2019: Class III Scholarship at University of Chinese Academy of Sciences (UCAS)
• Dec 2017: Merit Student at University of Chinese Academy of Sciences (UCAS)

Academic Service

• Conference Refereeing:
  NeurIPS-2024, IJCAI-2024, AAAI-2024, AAAI-2023, ICONIP-2023, ECML-2022
• Program Committee Member:
  AAAI-24 Student Program Program Committee
  AAAI-23 Student Program Program Committee
  

Teaching Assistant

• Summer 2024: MAT3007 Optimization
• Spring & Fall 2023: DDA4210 Advanced Machine Learning
• Fall 2022: MAT3300 Mathematical Modeling
• Summer 2022: EIE4006 Performance Evaluation of Communication Networks
• Spring 2022: STA3010 Regression Analysis
• Fall 2021: MAT4003 Number Theory
• Spring 2021: MAT4004 Graph Theory
• Fall 2020: MAT3280 Probability Theory