Back To Schedule
Monday, October 14 • 4:30pm - 4:45pm
HodgeNet: Flow Interpolation with Graph Neural Networks

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!


Recently, neural networks have been generalized to process data on graphs, with cutting-edge results in traditional tasks such as node classification and link prediction. These methods have all been formulated in a way suited only to data on the nodes of a graph, based on spectral graph theory. Using tools from algebraic topology, it is possible to reason about oriented data on higher-order structures by relying on the so-called Hodge Laplacian. Our goal is to develop techniques for applying the Hodge Laplacian to process data on higher-order graph structures using graph neural networks. To illustrate the practical value of this framework, we tackle the problem of flow interpolation: Given observations of flow over a subset of the edges of a graph, how can flow over the unobserved edges be inferred? We propose an architecture based on recurrent neural networks for performing flow interpolation, and demonstrate it on urban traffic data.


T. Mitchell Roddenberry

Presenter, Rice University

Santiago Segarra

Rice University

Monday October 14, 2019 4:30pm - 4:45pm CDT
BRC 103

Attendees (3)