ub.xmlui.mirage2.page-structure.muninLogoub.xmlui.mirage2.page-structure.openResearchArchiveLogo
    • EnglishEnglish
    • norsknorsk
  • Velg spraakEnglish 
    • EnglishEnglish
    • norsknorsk
  • Administration/UB
View Item 
  •   Home
  • Fakultet for naturvitenskap og teknologi
  • Institutt for matematikk og statistikk
  • Artikler, rapporter og annet (matematikk og statistikk)
  • View Item
  •   Home
  • Fakultet for naturvitenskap og teknologi
  • Institutt for matematikk og statistikk
  • Artikler, rapporter og annet (matematikk og statistikk)
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling

Permanent link
https://hdl.handle.net/10037/20258
DOI
https://doi.org/10.1109/TNNLS.2020.3044146
Thumbnail
View/Open
article.pdf (1.998Mb)
Accepted manuscript version (PDF)
Date
2020-12-31
Type
Journal article
Tidsskriftartikkel
Peer reviewed

Author
Bianchi, Filippo Maria; Grattarola, Daniele; Livi, Lorenzo; Alippi, Cesare
Abstract
In 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.
Publisher
IEEE
Citation
Bianchi, Grattarola, Livi, Alippi. Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling. IEEE Transactions on Neural Networks and Learning Systems. 2020
Metadata
Show full item record
Collections
  • Artikler, rapporter og annet (matematikk og statistikk) [354]
Copyright 2020 The Author(s)

Browse

Browse all of MuninCommunities & CollectionsAuthor listTitlesBy Issue DateBrowse this CollectionAuthor listTitlesBy Issue Date
Login

Statistics

View Usage Statistics
UiT

Munin is powered by DSpace

UiT The Arctic University of Norway
The University Library
uit.no/ub - munin@ub.uit.no

Accessibility statement (Norwegian only)