Jiaxuan You

Hi! I am a 4th year PhD student in Department of Computer Science, Stanford University. I'm advised by Prof. Jure Leskovec.
In the past, I have been fortunate enough to work with Prof. Jun Zhu as an undergrad in Tsinghua, with Prof. Stefano Ermon and Prof. David Lobell as a summer intern in 2016, with Kaiming He and Saining Xie as a summer intern in Facebook AI Research in 2019.

My research focuses on developing Machine Learning algorithms for graph/relational structured data, including generating/optimizing graph structures, developing new graph neural network architectures, and applying these techniques in various domains. See my research highlights for an overview.

Work 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.

Professional Services

• Senior Program Committee member: IJCAI 2021
  
• Program Committee member / Reviewer:
  Journals: IEEE Transactions on Pattern Analysis and Machine Intelligence (4 times), other IEEE Transactions (10+ times), VLDB Journal
  Conferences: ICML 2019, SIGGRAPH 2019, NeurIPS 2019 (top reviewer award), AAAI 2020, WWW 2020, ICWSM 2020, ICML 2020, NeurIPS 2020, ICLR 2021, ICWSM 2021
  Worshops: NeurIPS 2018/2019, ICLR 2019, ICML 2019/2020, on Graph/Relational representation learning

Code Platforms

• GraphGym: Platform for designing and evaluating Graph Neural Networks (GNN).
  [Code] [Paper] [Webpage]

Publications

1. 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]
2. Design Space for Graph Neural Networks
   Jiaxuan You, Rex Ying, Jure Leskovec
   34th Conference on Neural Information Processing Systems (NeurIPS 2020)
   Spotlight presentation
   [PDF] [Code] [Webpage]
3. 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 2020)
   [PDF] [Code] [Webpage]
4. 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]
5. 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)
   [PDF]
6. G2SAT: Learning to Generate SAT Formulas
   Jiaxuan You*, Haoze Wu*, Clark Barrett, Raghuram Ramanujan, Jure Leskovec.
   33th Conference on Neural Information Processing Systems (NeurIPS 2019)
   [PDF] [Code] [Webpage]
7. 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 2019)
   [PDF] [Code] [Webpage]
8. 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]
9. 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]
10. 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 2018)
    Spotlight presentation
    [PDF] [Code]
11. 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 2018)
    Spotlight presentation
    [PDF] [Code]
12. 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]
13. 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]
14. 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]
15. 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]
16. 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.
    [PDF]

Research Highlights

Latest papers

[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]

[Full image]

Design Space for Graph Neural Networks   (NeruIPS 2020)

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]

[Full image]

Handling Missing Data with Graph Neural Networks   (NeruIPS 2020)

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]

[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]

Deep generative models for graphs ("Graph decoder")

• GraphRNN: one of the first deep generative models for graphs


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
[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
[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]

Advanced representation learning models for graphs ("Graph encoder")



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]



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]

Applications that leverage graph structure



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]



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]



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.
[PDF]

Interdisciplinary research



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]



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.
[PDF] 

Misc.

• I was born on Jan 5th, 1997.