GFCN: A New Graph Convolutional Network Based on Parallel Flows

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 GraphFlow, is able to transfer CNN architectures to general graphs. To show the effectiveness of our approach, we test our method on the classical MNIST dataset, synthetic datasets on network information propagation and a news article classification dataset.

References in corpus (14)

• Efficient Estimation of Word Representations in Vector Space
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Discrete Signal Processing on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Learning Convolutional Neural Networks for Graphs
• Predicting multicellular function through multi-layer tissue networks
• Topology Adaptive Graph Convolutional Networks
• Identifying Infection Sources and Regions in Large Networks
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Adaptive Graph Convolutional Neural Networks
• A Hilbert Space Theory of Generalized Graph Signal Processing
• Graph Based Convolutional Neural Network
• Graph Normalizing Flows
• On the Universality of Jordan Centers for Estimating Infection Sources in Tree Networks