Graph Isomorphism Network

Introduced by Xu et al. in How Powerful are Graph Neural Networks?

Per the authors, Graph Isomorphism Network (GIN) generalizes the WL test and hence achieves maximum discriminative power among GNNs.

Source: How Powerful are Graph Neural Networks?

Read Paper See Code

Paper	Code	Results	Date	Stars

Task	Papers	Share
Graph Classification	8	13.79%
Node Classification	6	10.34%
Graph Learning	3	5.17%
Classification	3	5.17%
General Classification	3	5.17%
Graph Representation Learning	2	3.45%
Molecular Property Prediction	2	3.45%
Property Prediction	2	3.45%
Adversarial Attack	2	3.45%

This feature is experimental; we are continuously improving our matching algorithm.

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign