Jiaxuan You (尤佳轩)

Ph.D. student in Computer Science
Stanford University
Email: jiaxuan@stanford.edu
Office: Gates 441
[Google scholar] [Github]

Hi! I am a 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. Stefano Ermon and Prof. David Lobell as a summer intern. In Tsinghua, I have worked on Machine Learning supervised by Prof. Jun Zhu.
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.


  1. Jiaxuan You, Rex Ying, Jure Leskovec, Position-aware Graph Neural Networks, 36th International Conference on Machine Learning (ICML 2019).
  2. Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec, GNN Explainer: A Tool for Post-hoc Explanation of Graph Neural Networks, in submission.
  3. Zhihao Jia, Sina Lin, Rex Ying, Jiaxuan You, Jure Leskovec, Alex Aiken, Redundancy-Free Computation Graphs for Graph Neural Networks​, in submission.
  4. Jiaxuan You, Yichen Wang, Aditya Pal, Pong Eksombatchai, Chuck Rosenburg, Jure Leskovec, Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems, The Web Conference 2019 (WWW 2019).
    Acceptance rate 18%
  5. Jiaxuan You*, Bowen Liu*, Rex Ying, Vijay Pande, Jure Leskovec, Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation, 32th Conference on Neural Information Processing Systems (NeurIPS 2018).
    Spotlight presentation
    [PDF] [Code]
  6. Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec, Hierarchical Graph Representation Learning with Differentiable Pooling, 32th Conference on Neural Information Processing Systems (NeurIPS 2018).
    Spotlight presentation
  7. Jiaxuan You*, Rex Ying*, Xiang Ren, William L. Hamilton, Jure Leskovec, GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Model, 35th International Conference on Machine Learning (ICML 2018).
    [PDF] [Code]
  8. Jiaxuan You, Xiaocheng Li, Melvin Low, David Lobell, Stefano Ermon, Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data, 31th AAAI Conference on Artificial Intelligence (AAAI 2017) [oral].
    Best Student Paper Award (Computational Sustainability Track)
    [PDF] [Code] [Project Webpage]
  9. Jiaxuan You, Xiaocheng Li, Stefano Ermon, Scalable Crop Yield Prediction Approach by Combining Deep Learning with Remote Sensing Data, Best Big Data Solution in World Bank Big Data Innovation Challenge.
    1st place among 180+ teams
    [link] [Supplementary Materials]
  10. Jiaxuan You, Wei Guo, Yi Zhang et al., An Effective Simulation Model for Multi-line Metro Systems Based on Origin-destination Data, 19th IEEE International Conference on Intelligent Transportation Systems (ITSC 2016) [oral], the flagship conference in ITS society.
    As the only undergraduate attendee, I gave 4 talks and was warmly welcomed
    [PDF] [Photo]
  11. Wei Guo, Yi Zhang, Jiaxuan You et al., Travel Modal Choice Analysis for Traffic Corridors Based on Decision-theoretic Approaches, Journal of Central South University (SCI, EI), Nov 2015.
  12. Jiaxuan You, An Analysis for the Environmental Impact of Electric Vehicles in China Based on Empirical Investigation and Quantitative Estimation, Review of Economic Research 37 (2015), a Chinese Core Periodical.

Research Projects

P-GNN: Position-aware Graph Neural Networks  

In submission.

HAG: Redundancy-Free Computation Graphs for Graph Neural Networks​  

In submission.

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

Existing dynamic recommender systems often use out-of-the-box sequence models which are limited by speed and memory consumption, are often infeasible for production environments, and usually do not incorporate cross-session information. 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. We conduct extensive experiments on a public XING dataset and a large-scale Pinterest dataset of 6 million users with 1.6 billion interactions. We show that HierTCN is 2.5x faster than RNN-based models and uses 90% less data memory compared to TCN-based models.

[Full image]

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

Generating novel graph structures that optimize given objectives while obeying some given underlying rules is fundamental for chemistry, biology and social science research. Here we propose Graph Convolutional Policy Network (GCPN), a general graph convolutional network based model for goaldirected graph generation through reinforcement learning. The model is trained to optimize domain-specific rewards and adversarial loss through policy gradient, and acts in an environment that incorporates domain-specific rules. Experimental results show that GCPN can achieve 61% improvement on chemical property optimization over state-of-the-art baselines while resembling known molecules, and achieve 184% improvement on the constrained property optimization task.
[PDF] [Code

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

Recently, graph neural networks (GNNs) have revolutionized the field of graph representation learning through effectively learned node embeddings. 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. Our experimental results show that combining existing GNN methods with DiffPool yields an average improvement of 5-10% accuracy on graph classification benchmarks, compared to all existing pooling approaches, achieving a new state-of-the-art on four out of five benchmark datasets.

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

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. 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. In order to quantitatively evaluate the performance of GraphRNN, we introduce a benchmark suite of datasets, baselines and novel evaluation metrics based on Maximum Mean Discrepancy, which measure distances between sets of graphs. Our experiments show that GraphRNN significantly outperforms all baselines, learning to generate diverse graphs that match the structural characteristics of a target set, while also scaling to graphs 50× larger than previous deep models.
[PDF]  [Code

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. A novel dimensionality reduction method is proposed based on histogram calculation. By combining Gaussian Process with Convolutional Neural Networks, the model significantly outperforms traditional models, and we show that the features automatically extracted by deep learning models are much more effective than traditional hand-crafted features.
[PDF] [Code] [Project Webpage]

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

Metro systems are playing an increasing role in modern cities, and various management solutions are proposed to improve their efficiency. When analyzing the effects of those solutions, simulation proves to be an effective and cost-saving method. This paper presents an effective simulation model for multi-line metro systems based on the OD (origin-destination) data and the network connection data. The model is validated in the scenario of Beijing metro system, which proves its effectiveness in large-scale empirical implementation.

Professional Services

  • Conference Reviewer: ICML 2019, SIGGRAPH 2019, NeurIPS 2019
  • Worshop Reviewer: NeurIPS 2018 Workshop on Relational Representation Learning, ICML 2019 Workshop on Representation Learning on Graphs and Manifolds, ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data


  • I was born on Jan 5th, 1997.
  • I play drones. Some of the highlight videos are in my youtube channel.