My research interests span a wide array of topics around graph neural networks. Rather than focusing on a particular niche, I like to constantly look for new interesting and impactful problems. Some of the problems in graph neural networks that have caught my interest so far are:

  • Scalability: How do we scale GNNs to billion nodes graphs?
  • Dynamic Graphs: How do we learn on graphs that change over time?
  • Missing Node Features: How do apply GNNs to graphs where we only observe only a subset of features for each node (which is almost always the case in practice)?
  • Low Homophily Graphs: How do we design GNNs that work on graphs with low label homophily (where neighbors tend to have different labels)


Below is a list of my publications in reversed chronological order.


  1. arXiv
    On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
    ArXiv 2021
  2. ICML
    GRAND: Graph Neural Diffusion
    Proceedings of the 38th International Conference on Machine Learning, ICML 2021


  1. RecSys
    Tuning Word2vec for Large Scale Recommendation Systems
    Ben Chamberlain,  Emanuele Rossi, Dan Shiebler, Suvash Sedhain, and Michael Bronstein
    RecSys - 14th ACM Conference on Recommender Systems 2020
  2. ICML
    Temporal Graph Networks for Deep Learning on Dynamic Graphs
    Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein
    ICML Workshop on Graph Representation Learning 2020
  3. ICML
    SIGN: Scalable Inception Graph Neural Networks
    Emanuele Rossi, Fabrizio Frasca, Ben Chamberlain, Davide Eynard, Michael Bronstein, and Federico Monti
    ICML Workshop on Graph Representation Learning 2020


  1. KDD
    ncRNA Classification with Graph Convolutional Networks
    Emanuele Rossi, Federico Monti, Michael Bronstein, and Pietro Liò
    KDD Workshop on Deep Learning on Graphs 2019