Show simple item record

dc.contributor.authorBianchi, Filippo Maria
dc.contributor.authorGrattarola, Daniele
dc.contributor.authorLivi, Lorenzo
dc.contributor.authorAlippi, Cesare
dc.date.accessioned2021-01-11T11:36:02Z
dc.date.available2021-01-11T11:36:02Z
dc.date.issued2020-12-31
dc.description.abstractIn graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the GNN learns new node representations and fits them to a pyramid of coarsened graphs, which is computed offline in a preprocessing stage. NDP consists of three steps. First, a node decimation procedure selects the nodes belonging to one side of the partition identified by a spectral algorithm that approximates the MAXCUT solution. Afterward, the selected nodes are connected with Kron reduction to form the coarsened graph. Finally, since the resulting graph is very dense, we apply a sparsification procedure that prunes the adjacency matrix of the coarsened graph to reduce the computational cost in the GNN. Notably, we show that it is possible to remove many edges without significantly altering the graph structure. Experimental results show that NDP is more efficient compared to state-of-the-art graph pooling operators while reaching, at the same time, competitive performance on a significant variety of graph classification tasks.en_US
dc.identifier.citationBianchi, Grattarola, Livi, Alippi. Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling. IEEE Transactions on Neural Networks and Learning Systems. 2020en_US
dc.identifier.cristinIDFRIDAID 1862564
dc.identifier.doi10.1109/TNNLS.2020.3044146
dc.identifier.issn2162-237X
dc.identifier.issn2162-2388
dc.identifier.urihttps://hdl.handle.net/10037/20258
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.journalIEEE Transactions on Neural Networks and Learning Systems
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2020 The Author(s)en_US
dc.subjectVDP::Mathematics and natural science: 400::Mathematics: 410en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Matematikk: 410en_US
dc.subjectVDP::Technology: 500::Information and communication technology: 550en_US
dc.subjectVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550en_US
dc.titleHierarchical Representation Learning in Graph Neural Networks with Node Decimation Poolingen_US
dc.type.versionacceptedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record