Tutorial: Convolutional Neural Networks for Signals on Graphs

Title: Convolutional Neural Networks for Signals on Graphs

Date&Time16:00 – 18:00, December 26, 2021   Location: Prince Ballroom

Speaker:

Wenrui Dai (Shanghai Jiao Tong University)

Associate Professor, Department of Computer Science & Engineering

 

Abstract:

Signals of interest are supported on a graph structure in many real-world applications, including sensor networks, social networks, transportation systems, gene regulatory networks, and 3-D point clouds. It is of great importance to extend standard signal processing tools for representing signals on graphs. With the development of deep learning techniques, graph neural networks (GNNs) generalize the deep convolutional neural networks to signals on graphs and pave a new way for learning node-level and graph-level representations. In this talk, I will present the development and current trends of convolutional neural networks for signals on graphs. I will begin with the fundamental of graph signal processing and then elaborate the graph convolution and pooling operations developed in the spatial and spectral domains. Finally, I will introduce our recent works on multi-scale representation of signals on graphs via graph convolutional neural networks.

 

Biography:

Wenrui Dai received B.S., M.S., and Ph.D. degree in Electronic Engineering from Shanghai Jiao Tong University, Shanghai, China in 2005, 2008, and 2014. He is currently an associate professor at the Department of Computer Science and Engineering, Shanghai Jiao Tong University (SJTU). Before joining SJTU, he was with the faculty of the University of Texas Health Science Center at Houston from 2018 to 2019. He was a postdoctoral scholar with the Department of Biomedical Informatics, University of California, San Diego from 2015 to 2018 and a postdoctoral scholar with the Department of Computer Science and Engineering, SJTU from 2014 to 2015. His research interests include image/signal processing, learning-based image/video coding and predictive modeling. He has published 60 papers in prestigious journals like IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing, IEEE Transactions on Signal Processing and conferences like ICML and CVPR.