About Me

I work on designing and understanding machine learning algorithms that can be applied to novel problems, mostly involving data on graphs. I received a Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania, and an M.A. in Statistics from the Wharton School. I am currently a postdoctoral research associate working in the Electrical and Computer Engineering department at Rice University. Previously, I have been a postdoctoral scholar in the Electrical Engineering and Computer Sciences department at the University of California, Berkeley; a research intern at Facebook Artificial Intelligence Research, and a visiting scholar at TU Delft in the Netherlands.

The core of my research revolves around graph-structured data, with applications ranging from recommendation systems and authorship attribution to robotics, power grids, telecommunications, and distributed control. I have devised novel graph neural network architectures, based on both convolutional and non-convolutional filters. I have also worked with time-series data, adapting recurrent neural networks to graphs. In all cases, I have developed theoretical insights that help explain and understand the strengths and limitations of these graph neural network approaches. I have pioneered the use of graph neural network architectures in many novel domains, such as power grids, robotics, and distributed control.

I also have research experience in statistical signal processing. I have developed notions of ergodicity of graph stationary processes and a corresponding law of large numbers that leverages the underlying data structure to provide more accurate estimates. I have explored the bias-variance tradeoff, devising estimators that make better use of prior information. More recently, I have been working on leveraging machine learning in improving particle filtering (Monte Carlo methods) for the nonlinear estimation of dynamic systems.

A solid publication record (19 journal articles, and over 40 conference presentations, all peer-reviewed) and high citation numbers (>900 citations, h-index: 17, i10-index: 20) demonstrate my research skills and evidence of my capability to take on innovative problems, device novel solutions, and deliver meaningful results.

News

  • 6 April 2022: Invited talk "Graph Neural Networks" at the University of Rochester.

  • 8 March 2022: Invited talk "Graph Neural Networks" at the University of Maryland, College Park.

  • 8 September 2021: Invited talk "Graph Neural Networks" as part of the One World Signal Processing Seminars.

  • 16 August 2021: Started as a Postdoctoral Research Associate, working with Prof. Richard Baraniuk and Prof. Santiago Segarra, at Rice University.

  • 11 June 2021: Organizer of special session "Theoretical Foundations of Graph Neural Networks" at 46th IEEE ICASSP 2021.

  • 7 May 2021: Invited talk "(Some) Theoretical Results on Graph Neural Networks" at the Workshop on Geometric and Topological Representation Learning of ICLR 2021.

  • 28 April 2021: Webinar on "Graph Neural Networks" at the IEEE Signal Processing Society, based on the paper "Convolutional Neural Networks Architectures for Signals Supported on Graphs" which was among the Top 25 downloaded articles in 2020 for IEEE Transactions on Signal Processing.

  • 23 March 2021: The paper "Convolutional Neural Networks Architectures for Signals Supported on Graphs" is among the Top 25 downloaded articles in 2020 for IEEE Transactions on Signal Processing.

  • 5 March 2021: Invited talk "Graph Neural Networks" as part of the ComsoStat Day on Machine Learning in Astrophysics, Laboratoire CosmoStat, IRFU, CEA-Saclay, France. [Remote delivery]

  • 2 February 2021: Invited talk "Graph Neural Networks" as part of a five-class course on "Machine Learning on Graphs" at the University of the Republic, Montevideo, Uruguay. [Remote delivery]

  • 11 December 2020: Invited talk "Graph Neural Networks for Distributed Control" at the University of Buenos Aires, Argentina. [Remote delivery]

  • 18 September 2020: Invited talk "Graph Neural Networks" at the University of Texas, Austin, TX. [Remote delivery]

  • 15 September 2020: Started as a Postdoctoral Scholar, working with Prof. Somayeh Sojoudi, at the University of California, Berkeley.

  • 8 September 2020: Special session "Theoretical Foundations of Graph Neural Networks" proposal accepted at 46th IEEE ICASSP 2021.

  • 26 May 2020: Invited Talk "Graph Neural Networks" at Delft University of Technology, Delft, the Netherlands. [Remote delivery]

  • 4 May 2020: Presenter of the tutorial "Graph Neural Networks" at 45th IEEE ICASSP 2020, Barcelona, Spain. [Remote delivery]

  • 30 March 2020: Invited talk "Graph Neural Networks" at Dataminr, New York, NY. [Remote delivery]

  • 18 March 2020: Invited talk "Graph Neural Networks and Collaborative Intelligent Systems" at the University of Colorado, Boulder, CO. [Remote delivery]

  • 20 February 2020: Invited talk "Graph Neural Networks and Collaborative Intelligent Systems" at Johns Hopkins University, Baltimore, MD.

  • 14 November 2019: Invited talk "Graph Neural Networks" at Blackstone, New York, NY.

  • 18 October 2019: Awarded Neural Information Processing Systems travel award for attending NeurIPS 2019, Vancouver, BC.

  • 4 September 2019: Best student paper award at the 27th EUSIPCO 2019, A Coruña, Spain.