seongjunyun/Graph_Transformer_Networks

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1083 stars · 186 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Authors' PyTorch implementation of Graph Transformer Networks (GTN) from the NeurIPS 2019 paper, plus FastGTN with non-local operations. It learns meta-path graphs to improve graph neural networks on heterogeneous graphs.

Use cases

• implement graph transformer networks in pytorch
• learn meta-paths on heterogeneous graphs
• reproduce NeurIPS 2019 GTN paper results
• node classification on heterogeneous graph datasets
• compare GNN models with meta-path based transformers

When to choose

• you need the reference implementation of GTN or FastGTN for research
• you work with heterogeneous graphs and want meta-path learning
• you want a PyTorch codebase to extend for graph transformer experiments

When to avoid

• you need a production-ready, maintained GNN library
• you require a permissive license - the repo has none
• you work with homogeneous graphs only or need general-purpose deep learning tools

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning python graph-neural-networks graph-transformer pytorch research-code neurips-2019 meta-path heterogeneous-graphs algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="seongjunyun/Graph_Transformer_Networks")