{"url":"/dataset/wiki-cs","name":"Wiki-CS","full_name":null,"description_markdown":"Wiki-CS is a Wikipedia-based dataset for benchmarking Graph Neural Networks. The dataset is constructed from Wikipedia categories, specifically 10 classes corresponding to branches of computer science, with very high connectivity. The node features are derived from the text of the corresponding articles.  They were calculated as the average of pretrained GloVe word embeddings (Pennington et al., 2014), resulting in 300-dimensional node features.\r\n\r\nThe dataset has 11,701 nodes and 216,123 edges.\r\n\r\nSource: [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://arxiv.org/abs/2007.02901)\r\nImage Source: [https://arxiv.org/pdf/2007.02901v1.pdf](https://arxiv.org/pdf/2007.02901v1.pdf)","description_withheld":null,"homepage":"https://github.com/pmernyei/wiki-cs-dataset","introduced_date":"2020-07-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/wiki-cs-a-wikipedia-based-benchmark-for-graph","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","first_author":"Péter Mernyei","url":null},"license":null,"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Node Classification","url":"/task/node-classification","datasets_with_task":"/datasets/task/node-classification"},{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Node Clustering","url":"/task/node-clustering","datasets_with_task":"/datasets/task/node-clustering"}],"languages":[],"variants":["Wiki-CS"],"data_loaders":[{"repo":"https://github.com/rusty1s/pytorch_geometric","url":"https://pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html","frameworks":["pytorch"]},{"repo":"https://github.com/pmernyei/wiki-cs-dataset","url":"https://github.com/pmernyei/wiki-cs-dataset","frameworks":["pytorch"]}],"num_papers_in_archive":111,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/node-classification-on-wiki-cs","task":"Node Classification","dataset_variant":"Wiki-CS","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CGT","paper":"/paper/mitigating-degree-biases-in-message-passing","metrics":{"Accuracy":"84.61±0.53"},"code_links":[{"title":"nslab-cuk/community-aware-graph-transformer","url":"https://github.com/nslab-cuk/community-aware-graph-transformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scale-invariance-of-graph-neural-networks","title":"Scale Invariance of Graph Neural Networks","date":"2024-11-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mitigating-degree-biases-in-message-passing","title":"Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures","date":"2023-12-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/half-hop-a-graph-upsampling-approach-for","title":"Half-Hop: A graph upsampling approach for slowing down message passing","date":"2023-08-17","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}