Publications

You can also find my articles on my Google Scholar profile

* indicates equal contributions, $\dagger$ indicates corresponding author.

2024

• [ICLRW’24] Information Compensation: A Fix for Any-scale Dataset Distillation
  Peng Sun, Bei Shi, Xinyi Shang, Tao Lin$^\dagger$. 2024.
  [arXiv]
• [Preprint] GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
  Xinyi Shang*, Peng Sun* and Tao Lin$^\dagger$. 2024.
  [arXiv]

2023

• [ICML’23] Revisiting Weighted Aggregation in Federated Learning with Neural Networks
  Zexi Li, Tao Lin, Xinyi Shang, and Chao Wu. 2023.
  International Conference on Machine Learning, Honolulu, Hawai’i, July 23-29, 2023.
  [arXiv]

• [ICCV’23] No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
  Zexi Li, Xinyi Shang, Rui He, Tao Lin, Chao Wu. 2023.
  International Conference on Computer Vision, Paris, France, October 2-6, 2023.
  [arXiv]

• [Preprint] Federated Semi-Supervised Learning with Annotation Heterogeneity
  Xinyi Shang*, Gang Huang*, Yang Lu$^\dagger$, Jian Lou, Bo Han, Yiu-ming Cheung, and Hanzi Wang. 2023.
  [arXiv]

2022

• [IJCAI’22] Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features
  Xinyi Shang, Yang Lu$^\dagger$, Gang Huang, and Hanzi Wang
  IJCAI, pp.2218-2224, Vienna, Austria, July 23-29, 2022.
  International Joint Conference on Artificial Intelligence, pp.2218-2224, Vienna, Austria, July 23-29, 2022.
  [arXiv][code]

• [ICME’22 (Oral)] FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation
  Xinyi Shang, Yang Lu$^\dagger$, Yiu-ming Cheung, and Hanzi Wang
  ICME, pp.1-6, Taipei, Taiwan, July 18-22, 2022.
  IEEE International Conference on Multimedia and Expo, pp.1-6, Taipei, Taiwan, July 18-22, 2022.
  [arXiv][code]