Graph Signal Processing: Connections to Distributed Optimization and Deep Learning
Topic: Graph Signal Processing: Connections to Distributed Optimization and Deep Learning 图信号处理：连接分布式优化与深度学习
Speaker: Prof. Geert Leus (Delft University of Technology)
Host: Prof. Feng Yin (SSE, CUHK-Shenzhen)
Date and time: 15:00-16:00 on June 18, 2021 (Friday)
Topic: Research Seminar given by Prof. Geert Leus (TU Delft)
Time: Jun 18, 2021 15:00 PM Beijing, Shanghai, 9:00 AM The Netherlands
Join Zoom Meeting
Meeting ID: 910 2586 7349
Geert Leus received the M.Sc. and Ph.D. degree in Electrical Engineering from the KU Leuven, Belgium, in June 1996 and May 2000, respectively. Geert Leus is now an "Antoni van Leeuwenhoek" Full Professor at the Faculty of Electrical Engineering, Mathematics and Computer Science of the Delft University of Technology, The Netherlands. His research interests are in the broad area of signal processing, with a specific focus on wireless communications, array processing, sensor networks, and graph signal processing. Geert Leus received the 2021 EURASIP Individual Technical Achievement Award, a 2005 IEEE Signal Processing Society Best Paper Award, and a 2002 IEEE Signal Processing Society Young Author Best Paper Award. He is a Fellow of the IEEE and a Fellow of EURASIP. Geert Leus was a Member-at-Large of the Board of Governors of the IEEE Signal Processing Society, the Chair of the IEEE Signal Processing for Communications and Networking Technical Committee, a Member of the IEEE Sensor Array and Multichannel Technical Committee, a Member of the IEEE Big Data Special Interest Group, and the Editor in Chief of the EURASIP Journal on Advances in Signal Processing. He was also on the Editorial Boards of the IEEE Transactions on Signal Processing, the IEEE Transactions on Wireless Communications, the IEEE Signal Processing Letters, and the EURASIP Journal on Advances in Signal Processing. Currently, he is the Chair of the EURASIP Technical Area Committee on Signal Processing for Multisensor Systems, a Member of the IEEE Signal Processing Theory and Methods Technical Committee, an Associate Editor of Foundations and Trends in Signal Processing, and the Editor in Chief of EURASIP Signal Processing.
One of the cornerstones of the field of graph signal processing are graph filters, direct analogues of time-domain filters, but intended for signals defined on graphs. In this talk, we give an overview of the graph filtering problem. More specifically, we look at the family of finite impulse response (FIR) and infinite impulse response (IIR) graph filters and show how they can be implemented in a distributed manner. To further limit the communication and computational complexity of such a distributed implementation, we also generalize the state-of-the-art distributed graph filters to filters whose weights show a dependency on the nodes sharing information. These so-called edge-variant graph filters yield significant benefits in terms of filter order reduction and can be used for solving specific distributed optimization problems with an extremely fast convergence. Finally, we will overview how graph filters can be used in deep learning applications involving data sets with an irregular structure. Different types of graph filters can be used in the convolution step of graph convolutional networks leading to different trade-offs in performance and complexity. The numerical results presented in this talk illustrate the potential of graph filters in distributed optimization and deep learning.