Weihua Hu (胡 緯華)


I am currently working at Kumo.ai to productionize Graph Neural Networks (GNNs), with a paricular emphasis on using GNNs to answer a wide variety of future predictive queries on modern relational database.

I received a Ph.D. degree from the Department of Computer Science at Stanford, advised by Prof. Jure Leskovec. I built machine learning theory/methods/benchmarks for graph-structured data, aiming to improve diverse real-world applications, such as recommender systems, drug/material discovery, and weather forecasting. I am excited about applying (graph) machine learning to solve interesting and important real-world problems.

I received a B.E. in Mathematical Engineering in 2016, and an M.S. in Computer Science in 2018, both from the University of Tokyo, where I worked with Prof. Masashi Sugiyama on machine learning and Prof. Hirosuke Yamamoto on information theory. I also worked with Prof. Jun'ichi Tsujii and Prof. Hideki Mima on natural language processing.

[CV] [Google Scholar]



  1. Remi Lam*, Alvaro Sanchez-Gonzalez*, Matthew Willson*, Peter Wirnsberger*, Meire Fortunato*, Alexander Pritzel*, Suman Ravuri, Timo Ewalds, Ferran Alet, Zach Eaton-Rosen, Weihua Hu, Alexander Merose, Stephan Hoyer, George Holland, Jacklynn Stott, Oriol Vinyals, Shakir Mohamed, Peter Battaglia.
    GraphCast: Learning skillful medium-range global weather forecasting.

  2. Weihua Hu, Kaidi Cao, Kexin Huang, Edward W Huang, Karthik Subbian, Kenji Kawaguchi, Jure Leskovec.
    TuneUp: A Simple Improved Training Strategy for Graph Neural Networks.

  3. Shenyang Huang*, Farimah Poursafaei*, Jacob Danovitch, Matthias Fey, Weihua Hu, Emanuele Rossi, Jure Leskovec, Michael Bronstein, Guillaume Rabusseau, Reihaneh Rabbany.
    Temporal Graph Benchmark for Machine Learning on Temporal Graphs.
    [arXiv] [project page] [code]


  1. Weihua Hu
    On the Predictive Power of Graph Neural Networks
    Ph.D. Thesis in Computer Science, Stanford University.
    KDD Outstanding Doctoral Dissertation Award

  2. Weihua Hu, Rajas Bansal, Kaidi Cao, Nikhil Rao, Karthik Subbian, Jure Leskovec.
    Learning Backward Compatible Embeddings.
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Applied Data Science Track, 2022.
    [arXiv] [code]

  3. Shiori Sagawa*, Pang Wei Koh*, Tony Lee*, Irena Gao*, Sang Michael Xie, Kendrick Shen, Ananya Kumar, Weihua Hu, Michihiro Yasunaga, Henrik Marklund, Sara Beery, Etienne David, Ian Stavness, Wei Guo, Jure Leskovec, Kate Saenko, Tatsunori Hashimoto, Sergey Levine, Chelsea Finn, and Percy Liang.
    Extending the WILDS benchmark for unsupervised adaptation.
    International Conference on Learning Representations (ICLR), 2022. (oral)
    [arXiv] [project page] [code]


  1. Weihua Hu, Matthias Fey, Hongyu Ren, Maho Nakata, Yuxiao Dong, Jure Leskovec.
    OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs.
    KDD Cup 2021. NeurIPS competition 2022.
    Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, 2021.
    [arXiv] [project page] [kddcup 2021] [neurips 2022] [code]

  2. Weihua Hu, Muhammed Shuaibi, Abhishek Das, Siddharth Goyal, Anuroop Sriram, Jure Leskovec, Devi Parikh, C. Lawrence Zitnick.
    ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations.
    ICLR 2021 workshop at Deep Learning for Simulation. (Best paper award)
    [arXiv] [code] [talk]

  3. Lowik Chanussot*, Abhishek Das*, Siddharth Goyal*, Thibaut Lavril*, Muhammed Shuaibi*, Morgane Riviere, Kevin Tran, Javier Heras-Domingo, Caleb Ho, Weihua Hu, Aini Palizhati, Anuroop Sriram, Brandon Wood, Junwoong Yoon, Devi Parikh, C. Lawrence Zitnick, Zachary Ulissi.
    The Open Catalyst 2020 (OC20) Dataset and Community Challenges.
    ACS Catalysis, 2021.
    [arXiv] [project page] [code]

  4. C. Lawrence Zitnick, Lowik Chanussot, Abhishek Das, Siddharth Goyal, Javier Heras-Domingo, Caleb Ho, Weihua Hu, Thibaut Lavril, Aini Palizhati, Morgane Riviere, Muhammed Shuaibi, Anuroop Sriram, Kevin Tran, Brandon Wood, Junwoong Yoon, Devi Parikh, Zachary Ulissi.
    An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage.

  5. Pang Wei Koh*, Shiori Sagawa*, Henrik Marklund, Sang Michael Xie, Marvin Zhang, Akshay Balsubramani, Weihua Hu, Michihiro Yasunaga, Richard Lanas Phillips, Irena Gao, Tony Lee, Etienne David, Ian Stavness, Wei Guo, Berton A. Earnshaw, Imran S. Haque, Sara Beery, Jure Leskovec, Anshul Kundaje, Emma Pierson, Sergey Levine, Chelsea Finn, Percy Liang
    WILDS: A benchmark of in-the-wild distribution shifts.
    International Conference on Machine Learning (ICML), 2021. (long talk)
    [arXiv] [project page] [code]


  1. Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec.
    Open Graph Benchmark: Datasets for Machine Learning on Graphs.
    Neural Information Processing Systems (NeurIPS), 2020. (spotlight)
    [arXiv] [project page] [code] [talk]

  2. Weihua Hu*, Bowen Liu*, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec.
    Strategies for Pre-training Graph Neural Networks.
    International Conference on Learning Representations (ICLR), 2020. (spotlight)
    NeurIPS 2019 workshop at Graph Representation Learning. (oral)
    [OpenReview] [project page] [code]

  3. Hongyu Ren*, Weihua Hu*, Jure Leskovec.
    Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings.
    International Conference on Learning Representations (ICLR), 2020.
    [OpenReview] [project page] [code]


  1. Keyulu Xu*, Weihua Hu*, Jure Leskovec, Stefanie Jegelka.
    How Powerful are Graph Neural Networks?
    International Conference on Learning Representations (ICLR), 2019. (oral)
    [OpenReview] [arXiv] [code]

  2. Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto, Masashi Sugiyama.
    Unsupervised Discrete Representation Learning.
    Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Springer, Cham, 2019. 97-119.
    (Book chapter contribution of our ICML 2017 work.)


  1. Weihua Hu, Gang Niu, Issei Sato, Masashi Sugiyama.
    Does Distributionally Robust Supervised Learning Give Robust Classifiers?
    International Conference on Machine Learning (ICML), 2018.

  2. Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, Masashi Sugiyama.
    Co-teaching: Robust training of deep neural networks with noisy labels.
    Neural Information Processing Systems (NeurIPS), 2018.


  1. Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto, Masashi Sugiyama.
    Learning Discrete Representations via Information Maximizing Self Augmented Training.
    International Conference on Machine Learning (ICML), 2017.

  2. Weihua Hu, Hirosuke Yamamoto, Junya Honda.
    Worst-case Redundancy of Optimal Binary AIFV Codes and their Extended Codes.
    IEEE Transactions on Information Theory, vol.63, no.8, pp.5074-5086, August 2017.

  3. Takashi Ishida, Gang Niu, Weihua Hu, Masashi Sugiyama.
    Learning from Complementary Labels.
    Neural Information Processing Systems (NeurIPS), 2017.


  1. Weihua Hu, Hirosuke Yamamoto, Junya Honda.
    Tight Upper Bounds on the Redundancy of Optimal Binary AIFV Codes.
    IEEE International Symposium on Information Theory (ISIT), 2016.

  2. Weihua Hu, Jun'ichi Tsujii.
    A Latent Concept Topic Model for Robust Topic Inference Using Word Embeddings.
    The annual meeting of the Association for Computational Linguistics (ACL), 2016.

Workshop Organization


Professional Services



Work Experiences


Email: weihuahu [at] cs.stanford.edu
URL: https://weihua916.github.io/
Github: https://github.com/weihua916/