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.
Execute python -m graphsage.model
to run the HLS example.
It assumes that CUDA is not being used, but modifying the run functions in model.py
in the obvious way can change this.