Timezone: »

Principal Neighbourhood Aggregation for Graph Nets
Gabriele Corso · Luca Cavalleri · Dominique Beaini · Pietro Liò · Petar Veličković

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1707

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.

Author Information

Gabriele Corso (University of Cambridge)
Luca Cavalleri (University of Cambridge)
Dominique Beaini (Invivo AI)
Pietro Liò (University of Cambridge)
Petar Veličković (DeepMind)

More from the Same Authors