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.
Graph Convolutional Networks with Autoencoder-Based Compression and Multi-Layer Graph Learning / Giusti, L; Battiloro, C; Di Lorenzo, P; Barbarossa, S. - (2022), pp. 3593-3597. (Intervento presentato al convegno IEEE ICASSP 2022 tenutosi a Singapore) [10.1109/ICASSP43922.2022.9746161].
Graph Convolutional Networks with Autoencoder-Based Compression and Multi-Layer Graph Learning
Giusti, L;Battiloro, C;Di Lorenzo, P;Barbarossa, S
2022
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.File | Dimensione | Formato | |
---|---|---|---|
Giusti_Graph_2022.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.01 MB
Formato
Adobe PDF
|
2.01 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.