From 3ced3411e55bca803ed5ec5e1de6f62e1f21478f Mon Sep 17 00:00:00 2001 From: caojy1998 <84027205+caojy1998@users.noreply.github.com> Date: Tue, 20 Feb 2024 13:35:00 +0800 Subject: [PATCH] [Dataset] Add dataset ogbn-papers100M (#7096) Co-authored-by: Ubuntu --- python/dgl/graphbolt/impl/ondisk_dataset.py | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/python/dgl/graphbolt/impl/ondisk_dataset.py b/python/dgl/graphbolt/impl/ondisk_dataset.py index ca95bcf8f3f1..b1494ef37914 100644 --- a/python/dgl/graphbolt/impl/ondisk_dataset.py +++ b/python/dgl/graphbolt/impl/ondisk_dataset.py @@ -877,6 +877,16 @@ class BuiltinDataset(OnDiskDataset): Reverse edges are added to the original graph and duplicated edges are removed. + **ogbn-papers100M** + The ogbn-papers100M dataset is a directed graph, representing the citation + network between all Computer Science (CS) arXiv papers indexed by MAG. + See more details in `ogbn-papers100M + `_. + + .. note:: + Reverse edges are added to the original graph and duplicated + edges are removed. + **ogbn-products** The ogbn-products dataset is an undirected and unweighted graph, representing an Amazon product co-purchasing network. See more details @@ -916,7 +926,7 @@ class BuiltinDataset(OnDiskDataset): "ogbn-products", "ogbn-arxiv", ] - _large_datasets = ["ogb-lsc-mag240m"] + _large_datasets = ["ogb-lsc-mag240m", "ogbn-papers100M"] _all_datasets = _datasets + _large_datasets def __init__(self, name: str, root: str = "datasets") -> OnDiskDataset: