picture
  • Research
  • Publications
  • Software
  • Muhan Zhang (张牧涵)

    Email: muhan.zhang "at" hotmail "dot" com
    Google Scholar, Github


    Biography

    Muhan is a research scientist in Facebook AI Applied Research, focusing on general graph modeling problems at Facebook. He received his PhD degree in computer science from Washington University in St. Louis (2015-2019), advised by Prof. Yixin Chen. Before WashU, he obtained a bachelor degree from Shanghai Jiao Tong University as a member of the IEEE honor class, where he worked with Prof. Ya Zhang. He did an internship at the Core Data Science and Feed Science teams of Facebook as a research scientist in the summer of 2018, working with Anand Bhaskar.


    Research Interests

    Machine Learning, Data Mining, with particular interests in graph neural networks, link prediction, recommender systems, neural architecture search, etc.


    News

    8/24/2020: Excited to give a keynote talk at the DLG/MLG workshop of KDD 2020!

    5/15/2020: HAP paper accepted at KDD 2020!

    12/19/2019: IGMC paper accepted at ICLR 2020 as a spotlight presentation!

    12/14/2019: Presented our D-VAE paper at NeurIPS 2019!

    10/14/2019: Started full-time at Facebook!

    9/30/2019: Successfully defended my PhD thesis on GNN. Excited to complete PhD in 4 years!

    3/8/2019: Had a wonderful journey at Amazon's Graduate Research Symposium. Make friends with a lot of young talented!


    Publications

    Software

    IGMC (Inductive Graph-based Matrix Completion)

    Code for paper "Inductive Matrix Completion Based on Graph Neural Networks"

    D-VAE (DAG Variational Autoencoder)

    Code for paper "D-VAE: A Variational Autoencoder for Directed Acyclic Graphs" on NeurIPS 2019

    SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction)

    Code for paper "Link Prediction Based on Graph Neural Networks" on NeurIPS 2018

    DGCNN (Deep-Graph-CNN)

    Code for paper "An End-to-End Deep Learning Architecture for Graph Classification" on AAAI 2018

    Hyperlink Prediction Toolbox

    Code for paper "Beyond Link Prediction: Predicting Hyperlinks in Adjacency Space" on AAAI 2018

    WLNM (Weisfeiler-Lehman Neural Machine)

    Code for paper "Weisfeiler-Lehman Neural Machine for Link Prediction" on KDD 2017