Keyulu Xu

Email: keyulu [at] mit (dot) edu

Office: MIT Stata Center, 32-G480

Mail: 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430

I am a second-year graduate student in the EECS department at MIT and a member of CSAIL and the Machine Learning group.

My interests are in understanding the roots of the world, as well as creating new ones. I am currently pursuing these through deep learning and theory. I am fortunate to be advised by Stefanie Jegelka.

I studied mathematics and computer science as an undergraduate at University of British Columbia (UBC) in the beautiful city of Vancouver, where I was fortunate to be advised by Nick Harvey.

Aside from computer science, I enjoy artsy and adventurous activities, such as trading, Mahjong (gambling), novel writing, hunting, and people watching. I like to come up with general theory for everything. Currently, I am working on an ambitious project on creating a general framework for finance, politics and sociology.

Recent News


Email me if you have any questions about my papers or code, or if you would like to collaborate with me.

  1. Representation Learning on Graphs with Jumping Knowledge Networks
    Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, Stefanie Jegelka.
    International Conference on Machine Learning (ICML) 2018. Long talk.
    [arXiv] [Code (soon)]
  2. Distributional Adversarial Networks
    Chengtao Li, David Alvarez-Melis, Keyulu Xu, Stefanie Jegelka, Suvrit Sra.
    International Conference on Learning Representations workshop track (ICLR) 2018.
  3. Generating Random Spanning Trees via Fast Matrix Multiplication
    Nicholas J. A. Harvey and Keyulu Xu.
    Latin American Theoretical Informatics Symposium (LATIN) 2016.
    [PDF] [Web]


I have lived and worked in some of the most exciting cities in the world -- Vancouver, NYC, Tokyo and Shanghai.


Some recent talks by Keyulu, with video if available.

Representation Learning on Graphs with Jumping Knowledge Networks, at ICML 2018, Stockholm, Sweden. [Slides] [Video]
Generating Random Spanning Trees via Fast Matrix Multiplication, at LATIN 2016, Ensenada, Mexico. [Slides]