Luana Ruiz

Assistant Professor, Department of Applied Mathematics and Statistics, Johns Hopkins University

prof_pic.jpg

Wyman Park Building N452

Baltimore, MD 21211

lrubini1-at-jh-dot-edu

I am an assistant professor with the Department of Applied Mathematics and Statistics at Johns Hopkins University, the Mathematical Institute for Data Science (MINDS), and the Data Science and Artificial Intelligence Institute (DSAI). Before that, I was a METEOR and FODSI postdoctoral fellow working with Prof. Stefanie Jegelka at MIT, and a Google Research Fellow at the Simons Institute for the Theory of Computing. I obtained my PhD from the Electrical and Systems Engineering Department at Penn, where I was very fortunate to be advised by Prof. Alejandro Ribeiro.

My primary research interests are in the areas of machine learning and signal processing over networks. My current work focuses on large-scale graph information processing and graph neural networks. Please check my CV here and a selected list of publications below.

news

May 11, 2024 In Vienna to present our spotlight paper “A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs” (with Thien Le and Stefanie Jegelka) at ICLR’24.
Apr 30, 2024 Our papers on manifold neural networks (with Zhiyang Wang and Alejandro Ribeiro) were accepted to the IEEE Trasactions in Signal Processing. Check them out below!
Apr 14, 2024 In Seoul to present our paper “A Spectral Analysis of Graph Neural Networks on Dense and Sparse Graphs” (with Teresa Huang and Soledad Villar) at ICASSP’24.
Dec 9, 2023 Invited talk “Machine Learning on Large-Scale Graphs: Graphon NNs and Learning by Transference” at the Canadian Mathematical Society Winter Meeting.
Nov 16, 2023 Invited long talk “Large-Scale Graph Machine Learning: Tradeoffs, Guarantees and Dynamics” at DeepMath 2023.
Oct 17, 2023 New preprint A Local Graph Limits Perspective on Sampling-Based GNNs with Yeganeh and Amin.

selected publications

2024

  1. Stability to Deformations of Manifold Filters and Manifold Neural Networks
    Z. Wang, L. Ruiz, and A. Ribeiro
    IEEE Trans. Signal Process., 2024
  2. Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs
    Z. Wang, L. Ruiz, and A. Ribeiro
    IEEE Trans. Signal Process., 2024
  3. A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs (Spotlight)
    T. Le, L. Ruiz, and S. Jegelka
    In 12th ICLR, 7–11 may 2024
  4. A Spectral Analysis of Graph Neural Networks on Dense and Sparse Graphs
    L. Ruiz, N. Huang, and S. Villar
    In 49th ICASSP, 14-19 apr. 2024

2023

  1. Learning by Transference: Training Graph Neural Networks on Growing Graphs
    J. Cervino, L. Ruiz, and A. Ribeiro
    IEEE Trans. Signal Process., 14-19 apr. 2023
  2. Transferability Properties of Graph Neural Networks
    L. Ruiz, L. F. O. Chamon, and A. Ribeiro
    IEEE Trans. Signal Process., 14-19 apr. 2023
  3. Graph Neural Tangent Kernel: Convergence on Large Graphs
    S. Krishnagopal, and L. Ruiz
    In 40th ICML, 23-29 jul. 2023

2021

  1. Graph Neural Networks: Architectures, Stability and Transferability
    L. Ruiz, F. Gama, and A. Ribeiro
    Proc. IEEE, 23-29 jul. 2021
  2. Graphon Signal Processing
    L. Ruiz, L. F. O. Chamon, and A. Ribeiro
    Trans. Signal Process., 23-29 jul. 2021
  3. Stability of Neural Networks on Riemannian Manifolds (Best Paper Award)
    Z. Wang, L. Ruiz, and A. Ribeiro
    In 29th EUSIPCO, 23-27 aug. 2021
  4. Iterative Decoding for Compositional Generalization in Transformers
    L. Ruiz, J. Ainslie, and S. Ontañón
    arXiv:2110.04169 [cs.LG], 23-27 aug. 2021

2020

  1. Gated Graph Recurrent Neural Networks
    L. Ruiz, F. Gama, and A. Ribeiro
    Trans. Signal Process., 23-27 aug. 2020
  2. The Graphon Fourier Transform
    L. Ruiz, L. F. O. Chamon, and A. Ribeiro
    In 45th ICASSP, 4-8 may 2020
  3. Graphon Neural Networks and the Transferability of Graph Neural Networks
    L. Ruiz, L. F. O. Chamon, and A. Ribeiro
    In 34th NeurIPS, 6-12 dec. 2020

2019

  1. Gated Graph Convolutional Recurrent Neural Networks (Best Paper Award)
    L. Ruiz, F. Gama, and A. Ribeiro
    In 27th EUSIPCO, 2-6 sep. 2019