Corpus ID: 231698873

Identity-aware Graph Neural Networks

@inproceedings{You2021IdentityawareGN,
  title={Identity-aware Graph Neural Networks},
  author={Jiaxuan You and Jonathan M. Gomes-Selman and Rex Ying and J. Leskovec},
  booktitle={AAAI},
  year={2021}
}
Message passing Graph Neural Networks (GNNs) provide a powerful modeling framework for relational data. However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs. Here we develop a class of message passing GNNs, named Identity-aware Graph Neural Networks (ID-GNNs), with… Expand

Figures and Tables from this paper

A unifying point of view on expressive power of GNNs

References

SHOWING 1-10 OF 49 REFERENCES
Position-aware Graph Neural Networks
How Powerful are Graph Neural Networks?
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks
GNNExplainer: Generating Explanations for Graph Neural Networks
Relational Pooling for Graph Representations
Provably Powerful Graph Networks
On the equivalence between graph isomorphism testing and function approximation with GNNs
Graph Neural Networks for Social Recommendation
Residual Gated Graph ConvNets
...
1
2
3
4
5
...