{"url":"/dataset/dblp","name":"DBLP","full_name":"Citation Network Dataset","description_markdown":"The **DBLP** is a citation network dataset. The citation data is extracted from DBLP, ACM, MAG (Microsoft Academic Graph), and other sources. The first version contains 629,814 papers and 632,752 citations. Each paper is associated with abstract, authors, year, venue, and title.\r\nThe data set can be used for clustering with network and side information, studying influence in the citation network, finding the most influential papers, topic modeling analysis, etc.\r\n\r\nSource: [https://www.aminer.org/citation](https://www.aminer.org/citation)","description_withheld":null,"homepage":"https://www.aminer.org/citation","introduced_date":"2008-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"ArnetMiner: extraction and mining of academic social networks","first_author":null,"url":"https://doi.org/10.1145/1401890.1402008"},"license":{"name":"Unknown","url":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"},{"name":"Community Detection","url":"/task/community-detection","datasets_with_task":"/datasets/task/community-detection"},{"name":"Heterogeneous Node Classification","url":"/task/heterogeneous-node-classification","datasets_with_task":"/datasets/task/heterogeneous-node-classification"}],"languages":[],"variants":["DBLP (PACT) 14k","DBLP"],"data_loaders":[{"repo":"https://github.com/HeXiax/SSGNN","url":"https://github.com/HeXiax/SSGNN","frameworks":["pytorch"]}],"num_papers_in_archive":218,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-1","task":"Heterogeneous Node Classification","dataset_variant":"DBLP (PACT) 14k","rows":14,"metrics":["Micro-F1 (20% training data)","Macro-F1 (20% training data)","Macro-F1 (60% training data)","Micro-F1 (80% training data)","Macro-F1 (80% training data)"],"first_row_in_archive_order":{"model":"HAN","paper":"/paper/heterogeneous-graph-attention-network","metrics":{"Macro-F1 (20% training data)":"92.24%","Macro-F1 (60% training data)":"93.70%","Macro-F1 (80% training data)":"93.08%","Micro-F1 (20% training data)":"93.11%","Micro-F1 (80% training data)":"93.99%"},"code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/han"},{"title":"Jhy1993/HAN","url":"https://github.com/Jhy1993/HAN"},{"title":"JasonZhangzy1757/Heterogeneous-Graph-Attention-Network-HAN-PyTorch","url":"https://github.com/JasonZhangzy1757/Heterogeneous-Graph-Attention-Network-HAN-PyTorch"},{"title":"calderkatyal/CPSC483FinalProject","url":"https://github.com/calderkatyal/CPSC483FinalProject"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/node-classification-on-dblp","task":"Node Classification","dataset_variant":"DBLP","rows":6,"metrics":["Accuracy","Micro F1","Inference Time (ms)","Macro F1"],"first_row_in_archive_order":{"model":"GRACE","paper":"/paper/deep-graph-contrastive-representation","metrics":{"Accuracy":"84.2 ± 0.1"},"code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/grace"},{"title":"CRIPAC-DIG/GRACE","url":"https://github.com/CRIPAC-DIG/GRACE"},{"title":"ycremar/DIG-SSL","url":"https://github.com/ycremar/DIG-SSL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/link-prediction-on-dblp","task":"Link Prediction","dataset_variant":"DBLP","rows":3,"metrics":["AUC","AP"],"first_row_in_archive_order":{"model":"GLACE","paper":"/paper/gaussian-embedding-of-large-scale-attributed","metrics":{"AP":"98.4","AUC":"98.55"},"code_links":[{"title":"bhagya-hettige/GLACE","url":"https://github.com/bhagya-hettige/GLACE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/community-detection-on-dblp","task":"Community Detection","dataset_variant":"DBLP","rows":1,"metrics":["F1-Score"],"first_row_in_archive_order":{"model":"CommunityGAN","paper":"/paper/communitygan-community-detection-with","metrics":{"F1-Score":"0.153"},"code_links":[{"title":"SamJia/CommunityGAN","url":"https://github.com/SamJia/CommunityGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/faster-inference-time-for-gnns-using","title":"FIT-GNN: Faster Inference Time for GNNs Using Coarsening","date":"2024-10-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/r-gcn-the-r-could-stand-for-random","title":"R-GCN: The R Could Stand for Random","date":"2022-03-04","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/graph-representation-learning-beyond-node-and","title":"Graph Representation Learning Beyond Node and Homophily","date":"2022-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/deep-graph-contrastive-representation","title":"Deep Graph Contrastive Representation Learning","date":"2020-06-07","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bridging-the-gap-between-community-and-node","title":"Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection","date":"2019-12-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/non-local-attention-learning-on-large","title":"Non-local Attention Learning on Large Heterogeneous Information Networks","date":"2019-12-12","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/gaussian-embedding-of-large-scale-attributed","title":"Gaussian Embedding of Large-scale Attributed Graphs","date":"2019-12-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/heterogeneous-deep-graph-infomax","title":"Heterogeneous Deep Graph Infomax","date":"2019-11-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/learning-topological-representation-for","title":"Learning Topological Representation for Networks via Hierarchical Sampling","date":"2019-02-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/representation-learning-for-heterogeneous","title":"Representation Learning for Heterogeneous Information Networks via Embedding Events","date":"2019-01-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/communitygan-community-detection-with","title":"CommunityGAN: Community Detection with Generative Adversarial Nets","date":"2019-01-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/heterogeneous-graph-attention-network","title":"Heterogeneous Graph Attention Network","date":null,"rows_on_this_dataset":9,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"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."}