GFCN: A New Graph Convolutional Network Based on Parallel Flows
Speaker: Dr. Feng Ji, Nanyang Technological University
Time and Date: 2:00 - 3:00 pm, December 26,2019
Place: Room 530 of Scientific Building, Handan Campus, Fudan University
Abstract:
In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data. One major direction is based on spectral graph theory and graph signal processing. In this paper, we study the problem from a completely different perspective, by introducing parallel flow decomposition of graphs. The essential idea is to decompose a graph into families of non-intersecting one dimensional (1D) paths, after which, we may apply a 1D CNN along each family of paths. We demonstrate that the our method, which we call GFCN (graph flow convolutional network), is able to transfer CNN architectures to general graphs.
Biography:
Feng Ji received the B.S. degree in Mathematics in 2008 from National University of Singapore. He received his Ph.D. in Mathematics from National University of Singapore, in 2013. He is currently a research fellow in the School of Electrical and Electronic Engineering at Nanyang Technological University, Singapore. His research interests include graph signal processing, graph convolutional neural network, topology and geometry.