Graph Convolutional Networks With Autoencoder-Based Compression And Multi-Layer Graph Learning

This work aims to propose a novel architecture and training strategy for graph convolutional networks (GCN). The proposed architecture, named Autoencoder-Aided GCN (AA-GCN), compresses the convolutional features in an information-rich embedding at multiple hidden layers, exploiting the presence of a...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 3593 - 3597
Main Authors Giusti, Lorenzo, Battiloro, Claudio, Di Lorenzo, Paolo, Barbarossa, Sergio
Format Conference Proceeding
LanguageEnglish
Published IEEE 23.05.2022
Subjects
Acoustics
autoencoder
Computer architecture
Conferences
Convolution
Deep learning
graph convolutional networks
graph learning
graph signal processing
Robustness
Scalability
Training
Online AccessGet full text

Cover

More Information
Summary:This work aims to propose a novel architecture and training strategy for graph convolutional networks (GCN). The proposed architecture, named Autoencoder-Aided GCN (AA-GCN), compresses the convolutional features in an information-rich embedding at multiple hidden layers, exploiting the presence of autoencoders before the point-wise nonlinearities. Then, we propose a novel end-to-end training procedure that learns different graph representations per layer, jointly with the GCN weights and auto-encoder parameters. As a result, the proposed strategy improves the computational scalability of the GCN, learning the best graph representations at each layer in a data-driven fashion. Several numerical results on synthetic and real data illustrate how our architecture and training procedure compares favorably with other state-of-the-art solutions, both in terms of robustness and learning performance.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9746161