News & Events

Graph Neural Networks

Fernando Gama, PhD. Postdoctoral Research Associate in the department of electrical and computer engineering at Rice University, Houston, TX

1400 Wegmans Hall

Abstract: Graphs are generic models of signal structure that can help to learn in several practical problems. To learn from graph data, we need scalable architectures that can be trained on moderate dataset sizes and that can be implemented in a distributed manner. Drawing from graph signal processing, we define graph convolutions and use them to introduce graph neural networks (GNNs). We prove that GNNs are permutation equivariant and stable to perturbations of the graph, properties that explain their scalability and transferability. These results help understand the advantages of GNNs over linear graph filters. Introducing the problem of learning decentralized controllers, we discuss how GNNs naturally leverage the partial information structure inherent to distributed systems in order to learn useful efficient controllers. Using flocking as an illustrative example, we show that GNNs, not only successfully learn distributed actions that coordinate the team, but also transfer and scale to larger teams.

Bio: Fernando Gama received the electronic engineer degree from the University of Buenos Aires, Argentina, in 2013, the M.A. degree in statistics from the Wharton School, University of Pennsylvania, in 2017, and the Ph.D. degree in Electrical and Systems Engineering from the University of Pennsylvania, Philadelphia, PA, in 2020. He has been a visiting researcher at TU Delft, the Netherlands, in 2017, a research intern at Facebook Artificial Intelligence Research, Montreal, Canada, in 2018, and a postdoctoral scholar in the department of electrical engineering and computer sciences at the University of California, Berkeley, CA. He is currently a postdoctoral research associate in the department of electrical and computer engineering at Rice University, Houston, TX. He has been awarded a Fulbright scholarship for international students and he has received a best student paper award at EUSIPCO 2019. His first paper on GNNs has been one of the top 25 downloaded articles in 2020 for IEEE Transactions on Signal Processing.

Refreshments will be provided.