Davide Buffelli

Ph.D. Student · University of Padova · davide.buffelli [at] unipd.it

I'm a third year Ph.D. student in Information Engineering at the University of Padova, supervised by Professor Fabio Vandin. I have a broad interest in Deep Learning, with a current focus on techniques for structured data (geometric Deep Learning), and in particular Graph Neural Networks and Graph Representation Learning.

I hold a Bachelor's degree in Information Engineering and a Master's degree in Computer Engineering, both from the University of Padova. You check out my CV here.

I am currently a Research Scientist Intern at Meta AI in London. During my PhD I have been a visiting student in Professor Pietro Liò's group at the University of Cambridge, a visiting research in Dr. Bastian Rieck's group at Helmholtz Munich, and I've been an intern at Samsung AI Research (Cambridge).


09/2022 Our paper "SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks" has been accepted for publication at NeurIPS 2022!
09/2022 I am starting as a Research Scientist Intern at Meta AI in London!
08/2022 I have been awarded a Helmholtz Visiting Researcher Grant by HIDA. I will then visit Dr. Bastian Rieck at Helmholtz Munich to collaborate on exciting projects at the intersection of GNNs and topology!
07/2022 I have given a talk at the University of Cambridge about Graph Neural Networks and the problem of size-generalization. Check out the recording here.
04/2022 Our paper "Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach" has been accepted as oral at IJCNN 2022!
04/2022 I am joining the lab of Professor Pietro Liò at the University of Cambridge for a research visit until July 2022.

View Older News


  • Scalable Regularization of Scene Graph Generation Models using Symbolic Theories
    Davide Buffelli, Efthymia Tsamoura, Preprint, 2022.
    [PDF (arXiv)]
  • SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks
    Davide Buffelli, Pietro Liò, Fabio Vandin, Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022.
    [Paper to appear] [PDF (arXiv)] [Code]
  • Graph Representation Learning for Multi-Task Settings: a Meta-Learning Approach
    Davide Buffelli, Fabio Vandin, International Joint Conference on Neural Networks (IJCNN), 2022. (Oral)
    [Paper to appear] [PDF (arXiv)] [Code]
  • The Impact of Global Structural Information in Graph Neural Networks Applications
    Davide Buffelli, Fabio Vandin, Data (special issue "Knowledge Extraction from Data Using Machine Learning"), 2022.
    [Paper] [PDF (arXiv)] [Code]
  • Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation
    Davide Buffelli, Fabio Vandin, IEEE Sensors Journal, 2021.
    [Paper] [PDF (arXiv)] [Code]
  • A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
    Davide Buffelli, Fabio Vandin, NeurIPS Workshop on Meta-Learning (MetaLearn), 2020.
    [PDF] [PDF (arXiv; with Appendix)] [Video] [Slides] [Poster] [Code]

You can send me an email at davide.buffelli [at] unipd.it, and you can find me on Google Scholar, ORCID, LinkedIn, GitHub, and Twitter.