About Me

I received a Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania. I was advised by Prof. Alejandro Ribeiro. I am currently waiting for OPT approval to start a position as a Postdoctoral Scholar with Prof. Somayeh Sojoudi in the Electrical Engineering and Computer Sciences department at the University of California, Berkeley. I received an Electronic Engineering degree from the School of Engineering of the University of Buenos Aires, Argentina in 2013, and a M. A. in Statistics from the Wharton School in 2017. I have been a visiting researcher at TU Delft in 2017, and a research intern at Facebook Artificial Intelligence Research in 2018. I was awarded with a Fulbright scholarship for international students for 2014-2016.

My research interests currently lie on the field of machine learning for network data. More specifically, I am interested in developing collaborative intelligence. The fundamental objective is for a group of entities (modeled as nodes in a graph; could be a team of autonomous agents, sensors in a network, sources in a power grid, vehicles in a transportation network) to learn, from data, how to collaboratively accomplish a certain task. The challenge is that the nodes have access only to partial, local information acquired through exchanges with neighboring nodes, but need to coordinate a global solution for the entire team.

To tackle this problem, we have been developing tools within the context of graph neural networks (GNNs). We have been focusing on solutions that can be implemented locally on a given graph, exploiting the fact that nodes have computational capabilities. Our main focus is on characterizing the representation space of GNNs, that is, to understand what functions can be learned when using graph neural networks. This entails obtaining properties that all functions in this representation space have. For example, we have proved permutation equivariance and stability to perturbations which, together help explain the observed scalability and transferability of graph neural networks on homogeneous teams. While we keep investigating different characterizations of the representation space of graph neural networks, we have also been exploring diverse applications including control of teams of autonomous agents, power grids and wireless networks.


News

  • 8 August 2020: Start as a Postdoctoral Scholar, working with Prof. Somayeh Sojoudi, at the University of California, Berkeley. [pending OPT approval]
  • 12-15 July 2020: Organizer of special session "Learning from Network Data" at the IEEE SSP Workshop 2020. [postponed]
  • 26 May 2020: Invited talk "Graph Neural Networks" at the Delft University of Technology, Delft, the Netherlands. [remote delivery]
  • 4 May 2020: Presenter of tutorial "Graph Neural Networks" at the 45th IEEE ICASSP. [remote delivery]
  • 29 April 2020: Invited talk "Graph Neural Networks" at the University of Rochester, Rochester, NY. [postponed]
  • 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 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.
  • 4 September 2019: Best student paper award at the 27th EUSIPCO for "Gated Graph Convolutional Recurrent Neural Networks", A Coruña, Spain.
  • 22 July 2019: Awarded NSF student travel grant for attending the 27th EUSIPCO.
  • 5 July 2019: Invited talk "Graph Neural Networks" at Satellogic, Buenos Aires, Argentina.
  • 2 July 2019: Invited talk "Graph Neural Networks" at the National Scientific and Technical Research Council (CONICET), Buenos Aires, Argentina.
  • 23 May 2019: Awarded NSF student travel grant for attending IEEE DSW 2019.
  • 15 February 2019: Awarded IEEE Signal Processing Society travel grant for attending the 45th IEEE ICASSP.


Contact

E-mail : fgama@seas.upenn.edu
Skype : fg.fgama
In person : 3401 Walnut St
  4th Floor, Office 405
  Philadelphia, PA 19104
Other : LinkedIn

Google Scholar