Aggregation Graph Neural Networks

Fernando Gama, Antonio G. Marques, Alejandro Ribeiro, Geert Leus

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)
2 Downloads (Pure)


Graph neural networks (GNNs) regularize classical neural networks by exploiting the underlying irregular structure supporting graph data, extending its application to broader data domains. The aggregation GNN presented here is a novel GNN that exploits the fact that the data collected at a single node by means of successive local exchanges with neighbors exhibits a regular structure. Thus, regular convolution and regular pooling yield an appropriately regularized GNN. To address some scalability issues that arise when collecting all the information at a single node, we propose a multi-node aggregation GNN that constructs regional features that are later aggregated into more global features and so on. We show superior performance in a source localization problem on synthetic graphs and on the authorship attribution problem.

Original languageEnglish
Title of host publicationICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Place of PublicationPiscataway, NJ
Number of pages5
ISBN (Electronic)978-1-4799-8131-1
ISBN (Print)978-1-4799-8132-8
Publication statusPublished - 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12 May 201917 May 2019


Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.


  • convolutional neural networks
  • graph neural networks
  • graph signal processing
  • network data


Dive into the research topics of 'Aggregation Graph Neural Networks'. Together they form a unique fingerprint.

Cite this