graphfamily
R-GCN (Relational Graph Convolutional Network)
Graph convolutional network for relational data such as knowledge graphs, for link prediction and entity classification. Paper by Schlichtkrull et al. (2017).
Levelfamily
Classgraph
Parametersnot in the notes
Contextnot in the notes
Released17 Mar 2017
Opennessopen source
Runs onnot in the notes
Statusactive
R&D Topics
Identity
- Developer
- University of Amsterdam
- Family
- not in the notes
- Released
- 17 Mar 2017 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 Relation-specific graph convolution
- 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
ModelR-GCN (Relational Graph Convolutional Network)University of Amsterdam, graph
R-GCN (Relational Graph Convolutional Network)University of Amsterdam, graphR&D TopicsGraph Neural Networks and Graph TransformersKnowledge Graph Reasoning and Relational Foundation Models
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Graph Neural Networks and Graph TransformersNeural networks that learn from nodes, edges and their features for node classification,…produced byKnowledge Graph Reasoning and Relational Foundation ModelsModels that predict missing links and entities in multi-relational graphs or relational d…exemplar
Sources
- arxiv.org/abs/1703.06103 https://arxiv.org/abs/1703.06103
- 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/1703.06103 https://arxiv.org/html/1703.06103
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "R-GCN (Relational Graph Convolutional Network)", https://aurion.semai.id/models/r-gcn/, records of October 2026.