Xiangyu Shi

I am a master’s student at KTH Royal Institute of Technology, majoring in Machine Learning since 2023. I work as a research engineer at KTH advised by Sonia Horchidan and Prof. Paris Carbone, focusing on the Orb DB project and Conformal Prediction for Graph Embedding Spaces. My research interests include Graph Representation Learning, and Graph Neural Networks.

Before that, I obtained my Bachelor’s Degree in Computer Science and Technology from Harbin Institute of Technology (HIT) in 2023. I was a research assistant at Massive Data Computing Center of HIT supervised by Prof. Hongzhi Wang. Additionally, I served as a research assistant at Chinese University of Hong Kong, Shenzhen supervised by Prof. Zhizheng Wu.

selected publications

  1. AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy
    Chunnan Wang, Hongzhi Wang, and Xiangyu Shi
    In 2024 IEEE 40th International Conference on Data Engineering (ICDE) , 2024
  2. Audio compression-assisted feature extraction for voice replay attack detection
    Xiangyu Shi, Yuhao Luo, Li Wang, and 4 more authors
    arXiv preprint arXiv:2310.05813, 2023
  3. Fair Federated Learning with Multi-Objective Hyperparameter Optimization
    Chunnan Wang, Xiangyu Shi, and Hongzhi Wang
    ACM Trans. Knowl. Discov. Data, Jul 2024