Convolutional Neural Networks on Graphs


Convolutional neural networks have greatly improved state-of-the-art performances in computer vision and speech analysis tasks, due to its high ability to extract multiple levels of representations of data. In this talk, we are interested in generalizing convolutional neural networks from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, telecommunication networks, or words’ embedding. We present a formulation of convolutional neural networks on graphs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Numerical experiments demonstrate the ability of the system to learn local stationary features on graphs.

Feb 7, 2018 12:00 AM
Institute for Pure and Applied Mathematics, UCLA
Los Angeles, CA
Xavier Bresson
Assoc. Professor of Computer Science

Xavier Bresson is Associate Professor in Computer Science at NTU, Singapore. He is a leading researcher in the field of Graph Deep Learning, a new framework that combines graph theory and deep learning techniques.