# seongjunyun/Graph_Transformer_Networks

Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

Repository: https://github.com/seongjunyun/Graph_Transformer_Networks
Canonical: https://ross.abutalabs.com/products/graph_transformer_networks
Language: Jupyter Notebook
License Family: other
Last push: 2023-02-15T16:19:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2550, "days_push": 1295, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1083, forks 186 (observed 2026-08-28T04:03:31.244670+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: graph-neural-networks, graph-transformer, pytorch, research-code, neurips-2019, meta-path, heterogeneous-graphs, algorithms

## Member repositories
- seongjunyun/Graph_Transformer_Networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.244670+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:12.339009+00:00, confidence not recorded.
  - readme: https://github.com/seongjunyun/Graph_Transformer_Networks (fetched 2026-08-28T04:03:31.244670+00:00, sha 3dee36c61608)
- Data as of 2026-08-30T08:39:29.467469+00:00.