# gordicaleksa/pytorch-GAT

My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!

Repository: https://github.com/gordicaleksa/pytorch-GAT
Canonical: https://ross.abutalabs.com/products/pytorch-gat
Homepage: https://youtube.com/c/TheAIEpiphany
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: gat, graph-attention-networks, attention-mechanism, self-attention, pytorch, python, attention, pytorch-gat, gat-tutorial, deep-learning, graph-attention-network, pytorch-implementation, jupyter
Last push: 2022-11-17T14:21:18+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": 2076, "days_push": 1385, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2683, forks 357 (observed 2026-08-28T04:07:10.069684+00:00)

## What it is
A PyTorch implementation of the Graph Attention Network (GAT) paper by Veličković et al., built as an educational resource for learning about graph neural networks. It includes visualization tools for the Cora and PPI datasets, attention mechanisms, t-SNE embeddings, and entropy histograms.

## Use cases
- learn how graph attention networks work
- implement GAT from the original paper in pytorch
- visualize the Cora citation dataset
- understand attention mechanisms in graph neural networks
- train a GNN on node classification tasks
- study transductive and inductive graph learning examples

## When to choose
- you want to learn GNNs and GAT with well-commented educational code
- you need a reference PyTorch implementation of the GAT paper
- you want to visualize graph datasets and attention patterns

## When to avoid
- you need a production-ready or highly optimized GNN library
- you need support for many GNN architectures beyond GAT
- you want a maintained framework with frequent updates

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, data-visualization
- domain: deep-learning, machine-learning, tutorials, education
- platform: python
- tags: graph-neural-networks, graph-attention-networks, pytorch, cora, ppi, attention-mechanism, gnn, jupyter-notebook, gpu

## Member repositories
- gordicaleksa/pytorch-GAT (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:10.069684+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 2026-08-30T02:17:52.989323+00:00, confidence not recorded.
  - readme: https://github.com/gordicaleksa/pytorch-GAT (fetched 2026-08-28T04:07:10.069684+00:00, sha 5a1ca9aeec86)
  - homepage: https://youtube.com/c/TheAIEpiphany (fetched 2026-08-29T10:00:03.113835+00:00, sha a49038ff34c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.