We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains.

Classifying Signals on Irregular Domains via Convolutional Cluster Pooling / Porrello, Angelo; Abati, Davide; Calderara, Simone; Cucchiara, Rita. - 89:(2019). (Intervento presentato al convegno 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 tenutosi a Naha, Okinawa, Japan nel Tuesday, 16 April 2019).

Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

Angelo Porrello;Davide Abati;Simone Calderara;Rita Cucchiara
2019

Abstract

We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset. To this end, we introduce a Convolutional Cluster Pooling layer exploiting a multi-scale clustering in order to highlight, at different resolutions, locally connected regions on the input graph. Our proposal generalises well-established neural models such as Convolutional Neural Networks (CNNs) on irregular and complex domains, by means of the exploitation of the weight sharing property in a graph-oriented architecture. In this work, such property is based on the centrality of each vertex within its soft-assigned cluster. Extensive experiments on NTU RGB+D, CIFAR-10 and 20NEWS demonstrate the effectiveness of the proposed technique in capturing both local and global patterns in graph-structured data out of different domains.
2019
2019
22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019
Naha, Okinawa, Japan
Tuesday, 16 April 2019
89
Porrello, Angelo; Abati, Davide; Calderara, Simone; Cucchiara, Rita
Classifying Signals on Irregular Domains via Convolutional Cluster Pooling / Porrello, Angelo; Abati, Davide; Calderara, Simone; Cucchiara, Rita. - 89:(2019). (Intervento presentato al convegno 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019 tenutosi a Naha, Okinawa, Japan nel Tuesday, 16 April 2019).
File in questo prodotto:
File Dimensione Formato  
paper_521.pdf

Open access

Descrizione: Main paper
Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 1.55 MB
Formato Adobe PDF
1.55 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1171251
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 2
social impact