Graph summarization has received much attention lately, with various works tackling the challenge of defining pooling operators on data regions with arbitrary structures. These contrast the grid-like ones encountered in image inputs, where techniques such as max-pooling have been enough to show empirical success. In this work, we merge the Mapper algorithm with the expressive power of graph neural networks to produce topologically grounded graph summaries. We demonstrate the suitability of Mapper as a topological framework for graph pooling by proving that Mapper is a generalization of pooling methods based on soft cluster assignments. Building upon this, we show how easy it is to design novel pooling algorithms that obtain competitive results with other state-of-the-art methods. Additionally, we use our method to produce GNN-aided visualisations of attributed complex networks.

Deep Graph Mapper: Seeing Graphs Through the Neural Lens / Bodnar, C.; Cangea, C.; Lio, P.. - In: FRONTIERS IN BIG DATA. - ISSN 2624-909X. - 4:(2021). [10.3389/fdata.2021.680535]

Deep Graph Mapper: Seeing Graphs Through the Neural Lens

Lio P.
2021

Abstract

Graph summarization has received much attention lately, with various works tackling the challenge of defining pooling operators on data regions with arbitrary structures. These contrast the grid-like ones encountered in image inputs, where techniques such as max-pooling have been enough to show empirical success. In this work, we merge the Mapper algorithm with the expressive power of graph neural networks to produce topologically grounded graph summaries. We demonstrate the suitability of Mapper as a topological framework for graph pooling by proving that Mapper is a generalization of pooling methods based on soft cluster assignments. Building upon this, we show how easy it is to design novel pooling algorithms that obtain competitive results with other state-of-the-art methods. Additionally, we use our method to produce GNN-aided visualisations of attributed complex networks.
2021
graph classification; graph neural networks; graph summarization; mapper; pooling
01 Pubblicazione su rivista::01a Articolo in rivista
Deep Graph Mapper: Seeing Graphs Through the Neural Lens / Bodnar, C.; Cangea, C.; Lio, P.. - In: FRONTIERS IN BIG DATA. - ISSN 2624-909X. - 4:(2021). [10.3389/fdata.2021.680535]
File allegati a questo prodotto
File Dimensione Formato  
Bodnar_Deep-graph-mapper_2021.pdf

accesso aperto

Note: DOI 10.3389/fdata.2021.680535
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Creative commons
Dimensione 4.58 MB
Formato Adobe PDF
4.58 MB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1724051
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 11
social impact