Graph Convolutional Networks With Autoencoder-Based Compression And Multi-Layer Graph Learning
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{giusti2022graph,
author = {Lorenzo Giusti and Claudio Battiloro and Paolo Di Lorenzo and Sergio Barbarossa},
title = {{Graph Convolutional Networks With Autoencoder-Based Compression And Multi-Layer Graph Learning}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2022},
url = {https://openreview.net/forum?id=OBWdSIhLV1U},
}Loading related content...