graphsage/README.md

# 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 on small-graph benchmarks.
The code is also intended to be more extensible and easier to work with the 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).
Update README.md 2017-12-28 06:31:49 +08:00			`# 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 on small-graph benchmarks.`
			`The code is also intended to be more extensible and easier to work with the the TensorFlow version.`

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

			`#### Requirements`

			`pytorch >0.2 is required.`

			`#### Running examples`
Create README.md 2017-12-20 06:32:14 +08:00
			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).