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.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.