Need help with graphsage-simple?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.


Simple reference implementation of GraphSAGE.

561 Stars 167 Forks 12 Commits 16 Opened issues

Services available

Need anything else?

Reference PyTorch GraphSAGE Implementation

Author: William L. Hamilton

Basic reference PyTorch implementation of 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.


pytorch >0.2 is required.

Running examples


python -m graphsage.model
to run the Cora example. It assumes that CUDA is not being used, but modifying the run functions in
in the obvious way can change this. There is also a pubmed example (called via the
function in

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.