Graph convolutional and attention models for entity classification in multilayer networks

Abstract Graph Neural Networks (GNNs) are powerful tools that are nowadays reaching state of the art performances in a plethora of different tasks such as node classification, link prediction and graph classification. A challenging aspect in this context is to redefine basic deep learning operations...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Lorenzo Zangari, Roberto Interdonato, Antonio Calió, Andrea Tagarelli
Formato:	article
Lenguaje:	EN
Publicado:	SpringerOpen 2021
Materias:	Graph neural networks Multilayer networks Entity classification Applied mathematics. Quantitative methods T57-57.97
Acceso en línea:	https://doaj.org/article/d1bb34a33b554382b426d19c23350495
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d1bb34a33b554382b426d19c23350495
record_format	dspace
spelling	oai:doaj.org-article:d1bb34a33b554382b426d19c233504952021-11-14T12:12:01ZGraph convolutional and attention models for entity classification in multilayer networks10.1007/s41109-021-00420-42364-8228https://doaj.org/article/d1bb34a33b554382b426d19c233504952021-11-01T00:00:00Zhttps://doi.org/10.1007/s41109-021-00420-4https://doaj.org/toc/2364-8228Abstract Graph Neural Networks (GNNs) are powerful tools that are nowadays reaching state of the art performances in a plethora of different tasks such as node classification, link prediction and graph classification. A challenging aspect in this context is to redefine basic deep learning operations, such as convolution, on graph-like structures, where nodes generally have unordered neighborhoods of varying size. State-of-the-art GNN approaches such as Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) work on monoplex networks only, i.e., on networks modeling a single type of relation among an homogeneous set of nodes. The aim of this work is to generalize such approaches by proposing a GNN framework for representation learning and semi-supervised classification in multilayer networks with attributed entities, and arbitrary number of layers and intra-layer and inter-layer connections between nodes. We instantiate our framework with two new formulations of GAT and GCN models, namely ML-GCN and ML-GAT, specifically devised for general, attributed multilayer networks. The proposed approaches are evaluated on an entity classification task on nine widely used real-world network datasets coming from different domains and with different structural characteristics. Results show that both our proposed ML-GAT and ML-GCN methods provide effective and efficient solutions to the problem of entity classification in multilayer attributed networks, being faster to learn and offering better accuracy than the competitors. Furthermore, results show how our methods are able to take advantage of the presence of real attributes for the entities, in addition to arbitrary inter-layer connections between the nodes in the various layers.Lorenzo ZangariRoberto InterdonatoAntonio CalióAndrea TagarelliSpringerOpenarticleGraph neural networksMultilayer networksEntity classificationApplied mathematics. Quantitative methodsT57-57.97ENApplied Network Science, Vol 6, Iss 1, Pp 1-36 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Graph neural networks Multilayer networks Entity classification Applied mathematics. Quantitative methods T57-57.97
spellingShingle	Graph neural networks Multilayer networks Entity classification Applied mathematics. Quantitative methods T57-57.97 Lorenzo Zangari Roberto Interdonato Antonio Calió Andrea Tagarelli Graph convolutional and attention models for entity classification in multilayer networks
description	Abstract Graph Neural Networks (GNNs) are powerful tools that are nowadays reaching state of the art performances in a plethora of different tasks such as node classification, link prediction and graph classification. A challenging aspect in this context is to redefine basic deep learning operations, such as convolution, on graph-like structures, where nodes generally have unordered neighborhoods of varying size. State-of-the-art GNN approaches such as Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) work on monoplex networks only, i.e., on networks modeling a single type of relation among an homogeneous set of nodes. The aim of this work is to generalize such approaches by proposing a GNN framework for representation learning and semi-supervised classification in multilayer networks with attributed entities, and arbitrary number of layers and intra-layer and inter-layer connections between nodes. We instantiate our framework with two new formulations of GAT and GCN models, namely ML-GCN and ML-GAT, specifically devised for general, attributed multilayer networks. The proposed approaches are evaluated on an entity classification task on nine widely used real-world network datasets coming from different domains and with different structural characteristics. Results show that both our proposed ML-GAT and ML-GCN methods provide effective and efficient solutions to the problem of entity classification in multilayer attributed networks, being faster to learn and offering better accuracy than the competitors. Furthermore, results show how our methods are able to take advantage of the presence of real attributes for the entities, in addition to arbitrary inter-layer connections between the nodes in the various layers.
format	article
author	Lorenzo Zangari Roberto Interdonato Antonio Calió Andrea Tagarelli
author_facet	Lorenzo Zangari Roberto Interdonato Antonio Calió Andrea Tagarelli
author_sort	Lorenzo Zangari
title	Graph convolutional and attention models for entity classification in multilayer networks
title_short	Graph convolutional and attention models for entity classification in multilayer networks
title_full	Graph convolutional and attention models for entity classification in multilayer networks
title_fullStr	Graph convolutional and attention models for entity classification in multilayer networks
title_full_unstemmed	Graph convolutional and attention models for entity classification in multilayer networks
title_sort	graph convolutional and attention models for entity classification in multilayer networks
publisher	SpringerOpen
publishDate	2021
url	https://doaj.org/article/d1bb34a33b554382b426d19c23350495
work_keys_str_mv	AT lorenzozangari graphconvolutionalandattentionmodelsforentityclassificationinmultilayernetworks AT robertointerdonato graphconvolutionalandattentionmodelsforentityclassificationinmultilayernetworks AT antoniocalio graphconvolutionalandattentionmodelsforentityclassificationinmultilayernetworks AT andreatagarelli graphconvolutionalandattentionmodelsforentityclassificationinmultilayernetworks
_version_	1718429374929174528

Graph convolutional and attention models for entity classification in multilayer networks

Ejemplares similares