Corpus ID: 215745143

Principal Neighbourhood Aggregation for Graph Nets

@article{Corso2020PrincipalNA,
  title={Principal Neighbourhood Aggregation for Graph Nets},
  author={Gabriele Corso and Luca Cavalleri and Dominique Beaini and P. Lio' and Petar Velickovic},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.05718}
}
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… Expand
35 Citations

Figures and Tables from this paper

TOWARDS POWERFUL GRAPH NEURAL NETWORKS: DIVERSITY MATTERS
  • 2020
Parameterized Hypercomplex Graph Neural Networks for Graph Classification
  • Highly Influenced
  • PDF
Breaking the Expressive Bottlenecks of Graph Neural Networks
  • Highly Influenced
  • PDF
A Unified View on Graph Neural Networks as Graph Signal Denoising
  • 5
  • PDF
Structure-Aware Hierarchical Graph Pooling using Information Bottleneck
  • PDF
Graph Joint Attention Networks
  • PDF
Stochastic Aggregation in Graph Neural Networks
  • Highly Influenced
  • PDF
How hard is to distinguish graphs with graph neural networks?
  • 4
  • PDF
DEEPERGCN: TRAINING DEEPER GCNS
  • 2020
...
1
2
3
4
...

References

SHOWING 1-10 OF 62 REFERENCES
How Powerful are Graph Neural Networks?
  • 1,239
  • Highly Influential
  • PDF
Hierarchical Graph Representation Learning with Differentiable Pooling
  • 641
  • Highly Influential
  • PDF
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
  • 63
  • PDF
Can graph neural networks count substructures?
  • 37
  • PDF
Position-aware Graph Neural Networks
  • 114
  • PDF
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
  • 292
  • PDF
Adaptive Propagation Graph Convolutional Network
  • 6
  • PDF
Gated Graph Sequence Neural Networks
  • 1,396
  • PDF
Inductive Representation Learning on Large Graphs
  • 3,044
  • Highly Influential
  • PDF
...
1
2
3
4
5
...