graphfamily
GIN (Graph Isomorphism Network)
Graph neural network designed for maximal expressive power among message-passing networks, from the paper How Powerful are Graph Neural Networks? (Xu et al., 2018).
Levelfamily
Classgraph
Parametersnot in the notes
Contextnot in the notes
Released1 Oct 2018
Opennessopen source
Runs onnot in the notes
Statusactive
Identity
- Developer
- Massachusetts Institute of Technology, Stanford University
- Family
- not in the notes
- Released
- 1 Oct 2018 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- GNN Sum aggregation with MLPs, as expressive as the Weisfeiler-Lehman test
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- graph
- Output
- graph
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open source
- Licence
- MIT License sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Licence is that of the PyTorch Geometric implementation (MIT).
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelGIN (Graph Isomorphism Network)Massachusetts Institute of Technology, graph
GIN (Graph Isomorphism Network)Massachusetts Institute of Technology, graphUse Casesnone recorded
Who Runs Itnone recorded
Organisations 2
Sources
- arxiv.org/abs/1810.00826 https://arxiv.org/abs/1810.00826
- GitHub - pyg-team/pytorch_geometric: Graph Neural Network Library for PyTorch github.com https://github.com/pyg-team/pytorch_geometric
- pytorch-geometric.readthedocs.io/en/latest/modules/nn.html https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html
- huggingface.co/datasets/pwc-archive/methods https://huggingface.co/datasets/pwc-archive/methods
- arxiv.org/html/1810.00826 https://arxiv.org/html/1810.00826
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GIN (Graph Isomorphism Network)", https://aurion.semai.id/models/gin/, records of October 2026.