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.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.