Haoran Liu  (刘浩然)

Ph.D Student at Texas A&M University
Research Interests: Graph Neural Networks, Deep Learning

About me: Howdy👋! I am a Ph.D. student in the Department of Computer Science & Engineering at Texas A&M University, advised by Dr. James Caverlee. Previously, I was fortunate to work with Dr. Shuiwang Ji on geometric representation learning for biomedical data. Before coming to TAMU, I received master's and bachelor's degrees from Waseda University, Japan, and Southeast University, China. My current research focuses on temporal graph learning and adversarial attacks on graphs. I have a broad interest in graph/geometric learning, graph generation, and diffusion models. I enjoy running and bouldering when not doing research.
E-mail: liuhr99@tamu.edu
Google Scholar | Github | Twitter | LinkedIn
CV[PDF]


Education


Experiences

  1. Applied Scientist Intern at Amazon
    Automated Marketing Team
    Sep 2024 - Nov 2024      Seattle, WA

  2. Research Intern at NEC Labs America
    Machine Learning Department
    May 2024 - Aug 2024      Princeton, NJ
    Mentor: Dr. Martin Renqiang Min.

  3. Research Intern at NEC Labs America
    Machine Learning Department
    May 2023 - Aug 2023      Princeton, NJ
    Mentor: Dr. Martin Renqiang Min.

  4. Research Intern at Baidu Research
    Big Data Lab
    June 2020 - Aug 2020      Beijing, China
    Mentored by Dr. Haoyi Xiong and Prof. Dejing Dou.

Publications

    * indicates equal contribution.
  1. KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques [Paper]
    Rui Yang, Haoran Liu, Edison Marrese-Taylor, Qingcheng Zeng, Yu He Ke, Wanxin Li, Lechao Cheng, Qingyu Chen,
    James Caverlee, Yutaka Matsuo, Irene Li
    Preprint.

  2. Everything Perturbed All at Once: Enabling Differentiable Graph Attacks [Paper]
    Haoran Liu, Bokun Wang, Jianling Wang, Xiangjue Dong, Tianbao Yang, James Caverlee
    International Conference on World Wide Web (WWW), 2024. Short Paper Track.

  3. Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models [Paper]
    Meng Liu, Haoran Liu, Shuiwang Ji
    International Conference on Learning Representations (ICLR), 2023

  4. Learning Hierarchical Protein Representations via Complete 3D Graph Networks [Paper] [Code]
    Limei Wang*, Haoran Liu*, Yi Liu, Jerry Kurtin, Shuiwang Ji
    International Conference on Learning Representations (ICLR), 2023

  5. ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs [Paper] [Code]
    Limei Wang*, Yi Liu*, Yuchao Lin, Haoran Liu, Shuiwang Ji
    Conference on Neural Information Processing Systems (NeurIPS), 2022

  6. DIG: A Turnkey Library for Diving into Graph Deep Learning Research [Paper] [Code]
    Meng Liu, Youzhi Luo, Limei Wang, Yaochen Xie, Hao Yuan, Shurui Gui, Haiyang Yu, Zhao Xu, Jingtun Zhang, Yi Liu, Keqiang Yan,
    Haoran Liu, Cong Fu, Bora Oztekin, Xuan Zhang, Shuiwang Ji
    Journal of Machine Learning Research (JMLR), 2022

  7. Exploring the Common Principal Subspace of Deep Features in Neural Networks [Paper]
    Haoran Liu, Haoyi Xiong, Yaqing Wang, Haozhe An, Dejing Dou
    Machine Learning Journal (MLJ), 2022

  8. Edge-guided Hierarchically Nested Network for Real-time Semantic Segmentation [Paper]
    Yuqi Li, Sei-Ichiro Kamata, Haoran Liu
    IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 2019
    Best Paper Award

  9. Hybrid Featured based Pyramid Structured CNN for Texture Classification [Paper]
    Haoran Liu, Sei-Ichiro Kamata, Yuqi Li
    IEEE International Conference on Signal and Image Processing Applications (ICSIPA), 2019


Awards

  • D. E. Shaw Research Graduate and Postdoctoral Women’s Fellowship. 2023
  • Best Paper Award. ICSIPA. 2019.
  • IPS Special Scholarship for International Student. Waseda University. 2017-2018.
  • Foundation for the Advancement of Industry, Science and Technology (FAIS) Scholarship. 2017-2018.
  • Second Prize in National Undergraduate Electronics Design Contest. 2016.

Services


    Conference reviewer: NeurIPS (23', 24'), ICLR (23', 24', 25'), KDD (23'), SIGIR(23'), LoG (22', 23', 24'), NeurIPS Dataset and Benchmark Track (22', 23', 24'), CVPR (24', 25'), ICDM (20'), etc.
    Jounal reviewer: IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics.

Free Web Counters Since Sep, 2022

Proudly powered by Bootstrap