Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature spaces. We extend this theoretical framework to include continuous features—which occur regularly in real-world input domains and within the hidden layers of GNNs—and we demonstrate the requirement for multiple aggregation functions in this context. Accordingly, we propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degree-scalers (which generalize the sum aggregator). Finally, we compare the capacity of different models to capture and exploit the graph structure via a novel benchmark containing multiple tasks taken from classical graph theory, alongside existing benchmarks from real-world domains, all of which demonstrate the strength of our model. With this work, we hope to steer some of the GNN research towards new aggregation methods which we believe are essential in the search for powerful and robust models.

Principal neighbourhood aggregation for graph nets / Corso, G.; Cavalleri, L.; Beaini, D.; Lio, P.; Velickovic, P.. - (2020). (Intervento presentato al convegno Advances in Neural Information Processing Systems (was NIPS) tenutosi a Virtual; Online).

Principal neighbourhood aggregation for graph nets

Lio P.
;
2020

Abstract

Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on isomorphism tasks and countable feature spaces. We extend this theoretical framework to include continuous features—which occur regularly in real-world input domains and within the hidden layers of GNNs—and we demonstrate the requirement for multiple aggregation functions in this context. Accordingly, we propose Principal Neighbourhood Aggregation (PNA), a novel architecture combining multiple aggregators with degree-scalers (which generalize the sum aggregator). Finally, we compare the capacity of different models to capture and exploit the graph structure via a novel benchmark containing multiple tasks taken from classical graph theory, alongside existing benchmarks from real-world domains, all of which demonstrate the strength of our model. With this work, we hope to steer some of the GNN research towards new aggregation methods which we believe are essential in the search for powerful and robust models.
2020
Advances in Neural Information Processing Systems (was NIPS)
Graph theory; Graphic methods
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Principal neighbourhood aggregation for graph nets / Corso, G.; Cavalleri, L.; Beaini, D.; Lio, P.; Velickovic, P.. - (2020). (Intervento presentato al convegno Advances in Neural Information Processing Systems (was NIPS) tenutosi a Virtual; Online).
File allegati a questo prodotto
File Dimensione Formato  
Corso_Principal_2020.pdf

accesso aperto

Note: https://proceedings.neurips.cc/paper_files/paper/2020/file/99cad265a1768cc2dd013f0e740300ae-Paper.pdf
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 746.21 kB
Formato Adobe PDF
746.21 kB 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/11573/1719913
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 349
  • ???jsp.display-item.citation.isi??? 195
social impact