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.

The expressive power of pooling in Graph Neural Networks

Permanent link
https://hdl.handle.net/10037/33043
DOI
https://doi.org/10.48550/arXiv.2304.01575
Thumbnail
View/Open
article.pdf (592.9Kb)
Accepted manuscript version (PDF)
Date
2023
Type
Journal article
Tidsskriftartikkel
Peer reviewed

Author
Bianchi, Filippo Maria; Lachi, Veronica
Abstract
In Graph Neural Networks (GNNs), hierarchical pooling operators generate local summaries of the data by coarsening the graph structure and the vertex features. While considerable attention has been devoted to analyzing the expressive power of message-passing (MP) layers in GNNs, a study on how graph pooling affects the expressiveness of a GNN is still lacking. Additionally, despite the recent advances in the design of pooling operators, there is not a principled criterion to compare them. In this work, we derive sufficient conditions for a pooling operator to fully preserve the expressive power of the MP layers before it. These conditions serve as a universal and theoretically grounded criterion for choosing among existing pooling operators or designing new ones. Based on our theoretical findings, we analyze several existing pooling operators and identify those that fail to satisfy the expressiveness conditions. Finally, we introduce an experimental setup to verify empirically the expressive power of a GNN equipped with pooling layers, in terms of its capability to perform a graph isomorphism test.
Publisher
NeurIPS Proceedings
Citation
Bianchi, Lachi. The expressive power of pooling in Graph Neural Networks. Advances in Neural Information Processing Systems. 2023
Metadata
Show full item record
Collections
  • Artikler, rapporter og annet (matematikk og statistikk) [354]
Copyright 2023 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)