dmlc--dgl
8c750170e8
* simple implemention of GraphSAGE * update the abstract method and `torch.nn` modules are more utilized
Inductive Representation Learning on Large Graphs (GraphSAGE)
- Paper link: http://papers.nips.cc/paper/6703-inductive-representation-learning-on-large-graphs.pdf
- Author's code repo: https://github.com/williamleif/graphsage-simple. Note that the original code is simple reference implementation of GraphSAGE.
Requirements
- requests
bash pip install requests
Results
Run with following (available dataset: "cora", "citeseer", "pubmed")
python graphsage.py --dataset cora --gpu 0
- cora: ~0.8470
- citeseer: ~0.6870
- pubmed: ~0.7730