Jiaqing Xie

I am a third-year MSc student in Computer Science at ETH Zurich.

Previously, I obtained my B.Eng. in Electronics and Computer Science at The University of Edinburgh in 2022 . I am closely working with the following professors Tianfan Fu @ RPI, Yue Zhao @ USC, Roger Wattenhofer @ ETHZ, and Mrinmaya Sachan @ ETHZ.

Email  |  GitHub  |  Google Scholar

profile photo

Research

I'm interested the following areas:

  • AI4Science & GraphAI4Science
  • Interpretability of Large Language Models

    • Benchmarking Positional Encodings for GNNs and Graph Transformers
    Florian Grotschla, Jiaqing Xie, Roger Wattenhofer
    ArXiv
    arXiv / code

    DeepProtein: Deep Learning Library and Benchmark for Protein Sequence Learning
    Jiaqing Xie, Yue Zhao, Tianfan Fu
    Under Review @ Bioinformatics, NeurIPS AI4DrugX Spotlight, 2024
    arXiv / Library

    Applications in Protein Property Prediction, Localization Prediction, Protein-Protein Interaction, antigen epitope prediction, antibody paratope prediction, antibody developability prediction, etc.

    Graph Structure Learning via Lottery Hypothesis at Scale
    Yuxin Wang, Jiaqing Xie, Zhangyue Yin, Xiannian Hu, Yunhua Zhou, Xipeng Qiu, Xuanjing Huang
    Asian Conference on Machine Learning, 2023
    PMLR / Code

    Graph Structure Learning with Lottery Hypothesis shows robustness against graph attack.

    Workshop Papers
    Could Chemical Language Models benefit from Message Passing
    Jiaqing Xie, Ziheng Chi
    Proceedings of the 1st Workshop on Language + Molecules, ACL 2024
    ACL Anthology / Code

    How Graph Neural Networks could help pretrained Chemical LLMs learn features.


    Thank Dr. Jon Barron for sharing the source code of his personal page.