Convolutional Neural Network Architectures for Signals Supported on Graphs

DOI10.1109/TSP.2018.2887403MaRDI QIDQ4628260zbMATH OpenOpenAlexFDO

Authors Fernando Gama, Antonio G. Marques, Alejandro Ribeiro, G. Leus

Publication date 6 March 2019

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1805.00165

Mathematics Subject Classification ID

Applications of graph theory (05C90) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural network (GNN), which replaces linear time invariant filters with linear shift invariant graph filters to generate convolutional features and reinterprets pooling as a possibly nonlinear subsampling stage where nearby nodes pool their information in a set of preselected sample nodes. A key component of the architecture is to remember the position of sampled nodes to permit computation of convolutional features at deeper layers. The second architecture, dubbed aggregation GNN, diffuses the signal through the graph and stores the sequence of diffused components observed by a designated node. This procedure effectively aggregates all components into a stream of information having temporal structure to which the convolution and pooling stages of regular CNNs can be applied. A multinode version of aggregation GNNs is further introduced for operation in large scale graphs. An important property of selection and aggregation GNNs is that they reduce to conventional CNNs when particularized to time signals reinterpreted as graph signals in a circulant graph. Comparative numerical analyses are performed in a source localization application over synthetic and real-world networks. Performance is also evaluated for an authorship attribution problem and text category classification. Multinode aggregation GNNs are consistently the best performing GNN architecture.

Cited in

(6)

• Polynomial-based graph convolutional neural networks for graph classification
• K-plex cover pooling for graph neural networks
• CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
• Transferability of spectral graph convolutional neural networks
• Signal Processing on Simplicial Complexes
• Exponential stability of delayed neural networks with delayed sampled-data inputs: an extended bilateral looped functional approach

This page was built for publication: Convolutional Neural Network Architectures for Signals Supported on Graphs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4628260)