Jiaxuan You (尤佳轩)

Incoming Assistant Professor
Computer Science Department
University of Illinois at Urbana-Champaign
Email: jiaxuan@cs.stanford.edu
[Google Scholar] [Github]

I am currently an Adjunct Assistant Professor at UIUC CS, and a Senior Research Scientist at NVIDIA. I will join UIUC CS as a tenure-track Assistant Professor in 2024 Fall. I received my Ph.D. and M.S. degrees from Department of Computer Science, Stanford University, advised by Prof. Jure Leskovec. I was supported by JPMC PhD Fellowship and Baidu Scholarship during my PhD. My research leads to Kumo AI, where I built the first graph learning predictive system for relational databases as a core founding member from 2021 to 2023.

In the past, I have developed data-driven methods to study our interconnected world. I am broadly interested in deep learning for graphs, relational data, and databases. I am also excited about knowledge-augmented LLMs and multi-modal foundation models.
You may also check out a summary of my past research:
  • Core graph/relational learning methods: Learning from graphs [NeurIPS 2018b/2019b/2020a, ICML 2019, AAAI 2021]; Generating & optimizing graphs [ICML 2018, NeurIPS 2018a/2019a]
  • Democratize graph learning: Software and systems that make graph learning accessible to researchers and practitioners [GraphGym, PyG, Kumo AI]
  • Graph-inspired machine learning: Neural architecture design [ICML 2020], multi-task learning [ICLR 2022], deep learning with missing data [NeurIPS 2020b].
  • Interdisciplinary applications: crop yield prediction [AAAI 2017], drug discovery [NeurIPS 2018a], recommender systems [WWW 2019], financial transactions [KDD 2022], relational database [Kumo AI]
Ultimately, my research lab aims at building AGI in the digital world.
  • AI Agent: Exploring methodologies to enable AI to utilize tools and optimize itself based on those tools.
  • ML System: Strategies to enhance the inference and training of Large Language Models (LLMs) & Foundation Models, and facilitate their deployment and application.
  • Empowering AI with Relational Data: Investigating the utilization of AI to analyze and comprehend the interconnected digital world.
  • AI and Beyond: Delving into how AI research can profoundly reshape the future of scientific research and the broader human society.
  • We warmly welcome students to propose new directions and insights. Together, we will strive towards the goal of realizing AGI in the Digital World.

Prospective student

  • PhD openings: I am looking for multiple self-motivated PhD students starting in 2024 Fall (application occurs in Dec 2023). Students with strong ML or ML system background are preferred (e.g., could you explain data, model, tensor, pipeline, and FSDP parallelism?). If you are a prospective PhD student, I highly suggest reaching out to me early so that we can both check if there is a fit between us.
  • Intern openings: I am also looking for self-motivated remote intern students starting at any time. Similarly, students with strong ML or ML system background are preferred. I would prefer that you are interested in working with me as a PhD student in the long run.
  • Email format: "Interested in {position, e.g., Ph.D.} at {expected time, e.g., Fall 2024}”):
    - CV: Include your background, experiences, and future research interests.
    - Research: Summarize any projects, publications, and open-source software you have done.
    - Why Us?: Any research work from me that you are interested in. Mention any new topics (could be fully unrelated to my past research) that you would like to explore.
  • Google Form: You may also register your information on this Google Form. I will make sure to check out your information during the application process.


Work/Teaching Experience

  • Pinterest, Research Intern
    June 2018 - Sept 2018
    Mentor: Aditya Pal, Pong Eksombatchai, Chuck Rosenberg
    Developed large-scale dynamic recommender systems, published on WWW 2019.
  • Facebook AI Research (FAIR), Research Intern
    June 2019 - Feb 2020

    Mentor: Saining Xie, Kaiming He
    Graph Inspired Neural Network architecture design, published on ICML 2020.
  • Stanford CS224W, Head TA
    Jan 2021 - Apr 2021

    Course Materials: CS224W 2021 slides, CS224W 2021 Youtube playlist (live update every Tuesday/Thursday!)
    I lead the TA team to completely redesign the Stanford CS224W course in 2021. Now the course covers most of the state-of-the-art topics on graph representation learning.
    Among the slides I have created, I especially love Lecture 7 and Lecture 8 on Graph Neural Networks. There, based on the insights from my research, I gave general, in-depth and practical discussions on how to build a GNN system, which are greatly appreciated by the students. I gave a live lecture on Lecture 20 on GNN design space as well.
  • Kumo AI, Founding member
    2021 - June 2023
    I built the first proof-of-concept learning pipeline on relational database via graph learning. I have been leading the development of the relational learning engine for cloud databases at Kumo AI.

Professional Services

  • Senior Program Committee member: IJCAI 2021
  • Program Committee member / Reviewer:
    Journals: IEEE TPAMI (20+ times), other IEEE/ACM Journals (20+ times)
    Conferences: NeurIPS 2019(top reviewer award)/2020/2021/2022, ICML 2019/2020/2021/2022, ICLR 2021/2022, KDD 2021/2022, WWW 2020/2021/2022, AAAI 2020, IJCAI 2022, SIGGRAPH 2019, ICWSM 2020/2021,
    Worshops: NeurIPS 2018/2019, ICLR 2019, ICML 2019/2020, on Graph/Relational representation learning

Open-source Software


  1. AutoTransfer: AutoML with Knowledge Transfer -- An Application to Graph Neural Networks
    Kaidi Cao, Jiaxuan You, Jiaju Liu, Jure Leskovec
    International Conference on Learning Representations (ICLR 2023)
  2. ROLAND: Graph Learning Framework for Dynamic Graphs
    Jiaxuan You, Tianyu Du, Jure Leskovec
    28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022)
    [PDF] [Code]
  3. On the Opportunities and Risks of Foundation Models
    Rishi Bommasani, ..., Jiaxuan You, ..., Percy Liang
  4. Empowering Deep Learning with Graphs
    Jiaxuan You
    Ph.D. Thesis in Computer Science, 2021, Stanford University
  5. Identity-aware Graph Neural Networks
    Jiaxuan You, Jonathan Gomes-Selman, Rex Ying, Jure Leskovec
    35th AAAI Conference on Artificial Intelligence (AAAI 2021)
    [PDF] [Code] [Webpage]
  6. Design Space for Graph Neural Networks
    Jiaxuan You, Rex Ying, Jure Leskovec
    34th Conference on Neural Information Processing Systems (NeurIPS 2020a)
    Spotlight presentation
    [PDF] [Code] [Webpage]
  7. Handling Missing Data with Graph Neural Networks
    Jiaxuan You*, Xiaobai Ma*, Daisy Yi Ding*, Mykel Kochenderfer, Jure Leskovec
    34th Conference on Neural Information Processing Systems (NeurIPS 2020b)
    [PDF] [Code] [Webpage]
  8. Graph Structure of Neural Networks
    Jiaxuan You, Jure Leskovec, Kaiming He, Saining Xie
    37th International Conference on Machine Learning (ICML 2020)
    Long Oral
    [PDF] [Code] [Video Recording] [Slides]
  9. Redundancy-Free Computation for Graph Neural Networks​
    Zhihao Jia, Sina Lin, Rex Ying, Jiaxuan You, Jure Leskovec, Alex Aiken
    26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2020)
  10. G2SAT: Learning to Generate SAT Formulas
    Jiaxuan You*, Haoze Wu*, Clark Barrett, Raghuram Ramanujan, Jure Leskovec.
    33th Conference on Neural Information Processing Systems (NeurIPS 2019a)
    [PDF] [Code] [Webpage]
  11. GNNExplainer: A Tool for Post-hoc Explanation of Graph Neural Networks
    Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec
    33th Conference on Neural Information Processing Systems (NeurIPS 2019b)
    [PDF] [Code] [Webpage]
  12. Position-aware Graph Neural Networks
    Jiaxuan You, Rex Ying, Jure Leskovec
    36th International Conference on Machine Learning (ICML 2019)
    Long Oral
    [PDF] [Code] [Webpage] [Video Recording]
  13. Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
    Jiaxuan You, Yichen Wang, Aditya Pal, Pong Eksombatchai, Chuck Rosenberg, Jure Leskovec
    The Web Conference 2019 (WWW 2019)
    [PDF] [Code]
  14. Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
    Jiaxuan You*, Bowen Liu*, Rex Ying, Vijay Pande, Jure Leskovec
    32th Conference on Neural Information Processing Systems (NeurIPS 2018a)
    Spotlight presentation
    [PDF] [Code]
  15. Hierarchical Graph Representation Learning with Differentiable Pooling
    Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec
    32th Conference on Neural Information Processing Systems (NeurIPS 2018b)
    Spotlight presentation
    [PDF] [Code]
  16. GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Model
    Jiaxuan You*, Rex Ying*, Xiang Ren, William L. Hamilton, Jure Leskovec
    35th International Conference on Machine Learning (ICML 2018)
    [PDF] [Code]
  17. Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data
    Jiaxuan You, Xiaocheng Li, Melvin Low, David Lobell, Stefano Ermon
    31th AAAI Conference on Artificial Intelligence (AAAI 2017)
    Oral, Best Student Paper Award (Computational Sustainability Track)
    [PDF] [Code] [Project Webpage]
  18. Scalable Crop Yield Prediction Approach by Combining Deep Learning with Remote Sensing Data
    Jiaxuan You, Xiaocheng Li, Stefano Ermon
    Best Big Data Solution in World Bank Big Data Innovation Challenge
    1st place among 180+ teams
    [link] [Supplementary Materials]
  19. An Effective Simulation Model for Multi-line Metro Systems Based on Origin-destination Data
    Jiaxuan You, Wei Guo, Yi Zhang, et al.
    19th IEEE International Conference on Intelligent Transportation Systems (ITSC 2016)
    As the only undergraduate attendee, I gave talks for 4 papers and was warmly welcomed
    [PDF] [Photo]
  20. Travel Modal Choice Analysis for Traffic Corridors Based on Decision-theoretic Approaches
    Wei Guo, Yi Zhang, Jiaxuan You, et al.
    Journal of Central South University (SCI, EI), Nov 2015.

Research Highlights

Latest papers

Jiaxuan You[Full image]

Relational Multi-Task Learning: Modeling Relations between Data and Tasks   (ICLR 2022)

Here we introduce a novel relational multi-task learning setting where test data point may present auxiliary task labels. We develop MetaLink, where our key innovation is to build a knowledge graph that connects data points and tasks and thus allows us to leverage labels from auxiliary tasks.
[PDF] [Code]

Jiaxuan You[Full image]

Identity-aware Graph Neural Networks   (AAAI 2021)

Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with greater expressive power than the 1-WL test. ID-GNN offers a minimal but powerful solution to limitations of existing GNNs.
[PDF] [Code] [Webpage]

Jiaxuan You[Full image]

Design Space for Graph Neural Networks   (NeruIPS 2020a)

Here we define and systematically study the architectural design space for GNNs which consists of 315,000 different designs over 32 different predictive tasks. We release GraphGym, a powerful platform for exploring different GNN designs and tasks.
[PDF] [Code] [Webpage]

Jiaxuan You[Full image]

Handling Missing Data with Graph Neural Networks   (NeruIPS 2020b)

Here, we propose GRAPE, a general framework for feature imputation and label prediction in the presence of missing data. Our key innovation is to formulate the problem using a graph representation, where observations and features are two types of nodes, and the observed feature values are attributed edges.
[PDF] [Code] [Webpage]

Jiaxuan You[Full image]

Graph Structure of Neural Networks   (ICML 2020)

Here we systematically investigate how does the graph structure of neural networks affect their predictive performance. Our work opens new directions for the design of neural architectures and the understanding on neural networks in general.
[PDF] [Code] [Video Recording] [Slides]

  1. Deep generative models for graphs ("Graph decoder")
    • GraphRNN: one of the first deep generative models for graphs
    • Jiaxuan You

      GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Model   (ICML 2018)

      Here we propose GraphRNN, a deep autoregressive model that addresses the above challenges and approximates any distribution of graphs with minimal assumptions about their structure.
      [PDF] [Code]

    • GCPN: generate graph to satisfy user-provided goals, applied to molecule generation
    • Jiaxuan You[Full image]

      GCPN: Reinforcement Learning for Goal-Directed Molecular Graph Generation   (NeruIPS 2018)

      Here we propose Graph Convolutional Policy Network (GCPN), a general graph convolutional network based model for goal-directed graph generation through reinforcement learning.
      [PDF] [Code

    • G2SAT: highly scalable graph generator (over 25K nodes), applied to SAT formula generation
    • Jiaxuan You[Full image]

      G2SAT: Learning to Generate SAT Formulas
      (NeurIPS 2019)

      Here we present G2SAT, the first deep generative framework that learns to generate SAT formulas from a given set of input formulas.
      [PDF] [Code] [Webpage]

  2. Advanced representation learning models for graphs ("Graph encoder")
  3. Jiaxuan You

    DiffPool: Differentiable Pooling layer for Graph Networks   (NeurIPS 2018)

    Here we propose DiffPool, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion.
    [PDF] [Code]

    Jiaxuan You

    P-GNN: Position-aware Graph Neural Networks   (ICML 2019)

    Here we propose Position-aware Graph Neural Networks (PGNNs), a new class of GNNs for computing position-aware node embeddings which existing GNNs cannot represent.
    [PDF] [Code] [Webpage] [Video Recording]

  4. Applications that leverage graph structure
  5. Jiaxuan You

    HierTCN: Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems   (WWW 2019)

    Here we propose Hierarchical Temporal Convolutional Networks (HierTCN), a hierarchical deep learning architecture that makes dynamic recommendations based on users' sequential multi-session interactions with items.
    [PDF] [Code]

    Jiaxuan You

    GNNExplainer: A Tool for Post-hoc Explanation of Graph Neural Networks   (NeurIPS 2019)

    Here we propose GNNExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task.
    [PDF] [Code] [Webpage]

    Jiaxuan You

    HAG: Redundancy-Free Computation Graphs for Graph Neural Networks​   (KDD 2020)

    Here we propose Hierarchically Aggregated computation Graphs (HAGs), a new GNN representation technique that explicitly avoids redundancy by managing intermediate aggre- gation results hierarchically and eliminates repeated computations and unnecessary data transfers in GNN training and inference.

  6. Interdisciplinary research
  7. Jiaxuan You

    Crop Yield Prediction: Machine Learning over Satellite Images    (AAAI 2017)

    Crop yield prediction is central in ensuring the food security. We introduce the first deep learning based method to predict crop yield purely based on publicly available remote sensing data.
    [PDF] [Code] [Project Webpage]

    Jiaxuan You

    An Effective Simulation Model for Multi-line Metro Systems    (ITSC 2016)

    This paper presents an effective simulation model for multi-line metro systems based on the OD (origin-destination) data and the network connection data.