graph
GATv2
Revised graph attention layer that computes dynamic rather than static attention, from the paper How Attentive are Graph Attention Networks? (Brody et al., 2021).
Levelvariant
Classgraph
Parametersnot in the notes
Contextnot in the notes
Released30 May 2021
Opennessopen source
Runs onnot in the notes
Statusactive
Lineage
successor
GAT (Graph Attention Network) is the parent (successor)high confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
Identity
- Developer
- Technion - Israel Institute of Technology
- Family
- GAT (Graph Attention Network)
- Released
- 30 May 2021 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 Dynamic attention variant of GAT
- 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.
Industry Use Cases
No industry use case links this model.
Links
ModelGATv2Technion - Israel Institute of Technology, graph
GATv2Technion - Israel Institute of Technology, graphUse Casesnone recorded
Who Runs Itnone recorded
Sources
- arxiv.org/abs/2105.14491 https://arxiv.org/abs/2105.14491
- 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
- arxiv.org/html/2105.14491 https://arxiv.org/html/2105.14491
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GATv2", https://aurion.semai.id/models/gatv2/, records of October 2026.