https://github.com/williamleif/graphsage-simple

Simple reference implementation of GraphSAGE.
https://github.com/williamleif/graphsage-simple

Last synced: 1 day ago
JSON representation

Simple reference implementation of GraphSAGE.

• Host: GitHub
• URL: https://github.com/williamleif/graphsage-simple
• Owner: williamleif
• Created: 2017-12-19T21:41:35.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2020-05-11T20:58:32.000Z (over 4 years ago)
• Last Synced: 2024-08-03T15:17:28.856Z (3 months ago)
• Language: Python
• Size: 13.9 MB
• Stars: 981
• Watchers: 13
• Forks: 240
• Open Issues: 19
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Reference PyTorch GraphSAGE Implementation

### Author: William L. Hamilton

Basic reference PyTorch implementation of [GraphSAGE](https://github.com/williamleif/GraphSAGE).

This reference implementation is not as fast as the TensorFlow version for large graphs, but the code is easier to read and it performs better (in terms of speed) on small-graph benchmarks.

The code is also intended to be simpler, more extensible, and easier to work with than the TensorFlow version.

Currently, only supervised versions of GraphSAGE-mean and GraphSAGE-GCN are implemented. 

#### Requirements

pytorch >0.2 is required.

#### Running examples

Execute `python -m graphsage.model` to run the Cora example.

It assumes that CUDA is not being used, but modifying the run functions in `model.py` in the obvious way can change this.

There is also a pubmed example (called via the `run_pubmed` function in model.py).