Skip to content

Commit

Permalink
[Dataset] Contribute IGB-Homo dataset to node_classification.py (#7717)
Browse files Browse the repository at this point in the history
Co-authored-by: Muhammed Fatih BALIN <m.f.balin@gmail.com>
  • Loading branch information
BowenYao18 and mfbalin authored Aug 29, 2024
1 parent d6cf415 commit b4bd509
Show file tree
Hide file tree
Showing 2 changed files with 26 additions and 2 deletions.
12 changes: 10 additions & 2 deletions examples/graphbolt/node_classification.py
Original file line number Diff line number Diff line change
Expand Up @@ -363,9 +363,17 @@ def parse_args():
"--dataset",
type=str,
default="ogbn-products",
choices=["ogbn-arxiv", "ogbn-products", "ogbn-papers100M"],
choices=[
"ogbn-arxiv",
"ogbn-products",
"ogbn-papers100M",
"igb-hom-tiny",
"igb-hom-small",
"igb-hom-medium",
],
help="The dataset we can use for node classification example. Currently"
" ogbn-products, ogbn-arxiv, ogbn-papers100M datasets are supported.",
" ogbn-products, ogbn-arxiv, ogbn-papers100M and"
" igb-hom-[tiny|small|medium] datasets are supported.",
)
parser.add_argument(
"--mode",
Expand Down
16 changes: 16 additions & 0 deletions python/dgl/graphbolt/impl/ondisk_dataset.py
Original file line number Diff line number Diff line change
Expand Up @@ -979,6 +979,16 @@ class BuiltinDataset(OnDiskDataset):
.. note::
Reverse edges are added to the original graph.
**igb-hom-[tiny|small|medium]**
The igb-hom-[tiny|small|medium] dataset is a homogeneous citation network,
which is designed for developers to train and evaluate GNN models with
high fidelity. See more details in `igb-hom-[tiny|small|medium]
<https://github.com/IllinoisGraphBenchmark/IGB-Datasets>`_.
.. note::
Self edges are added to the original graph.
Node features are stored as float32.
Parameters
----------
name : str
Expand All @@ -1004,12 +1014,18 @@ class BuiltinDataset(OnDiskDataset):
"ogbn-products-seeds",
"ogbn-arxiv",
"ogbn-arxiv-seeds",
"igb-hom-tiny",
"igb-hom-tiny-seeds",
"igb-hom-small",
"igb-hom-small-seeds",
]
_large_datasets = [
"ogb-lsc-mag240m",
"ogb-lsc-mag240m-seeds",
"ogbn-papers100M",
"ogbn-papers100M-seeds",
"igb-hom-medium",
"igb-hom-medium-seeds",
]
_all_datasets = _datasets + _large_datasets

Expand Down

0 comments on commit b4bd509

Please sign in to comment.