About
Hello~ I am Xinyi, a Ph.D. candidate at University College London (UCL), luckily supervised by Prof. Jing-Hao Xue. My research is mainly funded by CSC and UCL jointly. Before that, I received my master’s degree with honors in Computer Science from Xiamen University (XMU), fortunately supervised by Dr. Yang Lu. My main research interests lie in Generalized Deep Learning under imperfect environments and Efficient Deep Learning.
Research Interests
- Generalized Deep Learning
- Federated Learning
- Long-tailed Learning
- Semi-supervised Learning
- Out-of-distribution Generalization
- Underspecification Data
- Efficient Deep Learning
- Dataset Distillation
- Data-Efficient Learning
Information
- Email: xinyi.shang.23 [at] ucl.ac.uk
- Github: https://github.com/shangxinyi/
- Google Scholar: https://scholar.google.com/
Recent News
- May 19 2023: Receive the Outstanding Master Thesis Award.
- Mar 28 2023: Receive the PhD offer from University College London (UCL) supported by scholarship!!
- Nov 23 2022: Start research intern at Westlake University, supervised by Prof. Tao Lin.
- Sep 29 2022: Get the China National Scholarship.
- Apr 21 2022: One IJCAI paper “Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features” is accepted.
- Mar 6 2022: One ICME paper “FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation” is accepted as oral paper.
Academic Service
- Conference Reviewer: International Conference on Learning Representations (ICLR) 2025, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2025, International Joint Conference on Artificial Intelligence (IJCAI) 2024.
- Journal Reviewer: IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), ACM Computing Surveys (CSUR), IEEE Transactions on Cybernetics (ITC), IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI).