Hao Liu

Ph.D. Candidate at Washington University in St. Louis.

hl.jpg

Email: liuhao @ wustl.edu

Office: Mckelvey Hall 2010

Saint Louis, MO

I’m a fifth year Ph.D. candidate at Washington University in St. Louis. I’m fortunately advised by Dr. Yixin Chen. Prior to joining WashU, I obtained my bachelor’s degree in Mathematics from Beijing Normal University. My research primarily focuses on addressing few-shot and zero-shot challenges in graph and tabular domains. Additionally, I have a keen interest in applying these to real-world clinical problems. Please check out my resume here: Resume.

My recent interest is to design a graph foundation model leveraging LLMs. OneForAll enables a single GNN to work on classification tasks across various datasets and task-levels. GOFA introduces a generative graph foundation model that combines GNN and LLM layers for large-scale pretraining through graph-level next-token prediction.

selected works

  1. GOFA_taskfig.jpg
    GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
    *Lecheng Kong, *Jiarui Feng, *Hao Liu, and 4 more authors
    arXiv preprint arXiv:2407.09709, 2024
  2. TAGLAS_overview.jpg
    TAGLAS: An atlas of text-attributed graph datasets in the era of large graph and language models
    Jiarui Feng, *Hao Liu, *Lecheng Kong, and 2 more authors
    arXiv preprint arXiv:2406.14683, 2024
  3. OFA_mainfig.jpg
    One for All: Towards Training One Graph Model for All Classification Tasks
    *Hao Liu, *Jiarui Feng, *Lecheng Kong, and 4 more authors
    In The Twelfth International Conference on Learning Representations, 2024
  4. COLA_mainfig.jpg
    Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks
    Hao Liu, Jiarui Feng, Lecheng Kong, and 3 more authors
    In The Web Conference 2024, 2024
  5. NeurIPS TRL 2023
    TabContrast: A Local-Global Level Method for Tabular Contrastive Learning
    Hao Liu, Yixin Chen, Bradley Fritz, and 1 more author
    In NeurIPS 2023 Second Table Representation Learning Workshop, 2023
  6. NeurIPS 2023
    MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
    Lecheng Kong, Jiarui Feng, Hao Liu, and 3 more authors
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
  7. NeurIPS 2023
    Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
    Jiarui Feng, Lecheng Kong, Hao Liu, and 4 more authors
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023

education

  • 2019.09 - now, Ph.D. student, Computer Science and Engineering, Washington University in St. Louis.
  • 2015.09 - 2019.06, Bachelor, Mathematics, Beijing Normal University.

personal

  • I'm from Jilin, China.
  • 🎮 Roguelike Game Lover.