avatar

Langzhang Liang

Ph.D. Student
Fudan University
lazylzliang@gmail.com


About Me

I am a first-year Ph.D. student in AI at Fudan University, advised by Prof. Zenglin Xu. I previously spent a year at KAIST and completed my master’s degree at Harbin Institute of Technology, Shenzhen (supervised by Prof. Zenglin Xu). My master’s research focused on graph neural networks; I am currently transitioning to AI for Science, with a particular interest in computational drug discovery. I also receive guidance from Prof. Shirui Pan at Griffith University.

Research Interests

News

Publications

  1. ICML
    Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
    Langzhang Liang, Fanchen Bu, Zixing Song, Zenglin Xu, Shirui Pan, Kijung Shin
    International Conference on Machine Learning (ICML), 2025.
    PDF Poster

  2. ICML
    Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
    Langzhang Liang, Sunwoo Kim, Kijung Shin, Zenglin Xu, Shirui Pan, Yuan Qi
    International Conference on Machine Learning (ICML), 2024.
    PDF Poster

  3. NeurIPS
    Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily
    Langzhang Liang, Xiangjing Hu, Zenglin Xu, Zixing Song, Iwrin King
    Advances in Neural Information Processing Systems (NeurIPS), 2023.
    PDF Poster

  4. TKDE
    Tackling Long-Tailed Distribution Issue in Graph Neural Networks via Normalization
    Langzhang Liang, Zenglin Xu, Zixing Song, Iwrin King, Yuan Qi, Jieping Ye
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023.
    PDF Poster

Services

Conference Reviewers

Journal Reviewers