{"url":"/dataset/collab","name":"COLLAB","full_name":null,"description_markdown":"**COLLAB** is a scientific collaboration dataset. A graph corresponds to a researcher’s ego network, i.e., the researcher and its collaborators are nodes and an edge indicates collaboration between two researchers. A researcher’s ego network has three possible labels, i.e., High Energy Physics, Condensed Matter Physics, and Astro Physics, which are the fields that the researcher belongs to. The dataset has 5,000 graphs and each graph has label 0, 1, or 2.\r\n\r\nSource: [1 Introduction](https://arxiv.org/abs/2006.11165)","description_withheld":null,"homepage":"https://ls11-www.cs.tu-dortmund.de/staff/morris/graphkerneldatasets","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/deep-graph-kernels","title":"Deep Graph Kernels","first_author":"Pinar Yanardag","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Link Prediction","url":"/task/link-prediction","datasets_with_task":"/datasets/task/link-prediction"},{"name":"Graph Classification","url":"/task/graph-classification","datasets_with_task":"/datasets/task/graph-classification"}],"languages":[],"variants":["COLLAB"],"data_loaders":[{"repo":"https://github.com/dmlc/dgl","url":"https://docs.dgl.ai/api/python/dgl.data.html#dgl.data.TUDataset","frameworks":["pytorch","tf","mxnet"]},{"repo":"https://github.com/danielegrattarola/spektral","url":"https://graphneural.network/datasets/#tudataset","frameworks":["tf"]}],"num_papers_in_archive":259,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/graph-classification-on-collab","task":"Graph Classification","dataset_variant":"COLLAB","rows":39,"metrics":["Accuracy","Accuracy (10-fold)"],"first_row_in_archive_order":{"model":"U2GNN (Unsupervised)","paper":"/paper/unsupervised-universal-self-attention-network","metrics":{"Accuracy":"95.62%"},"code_links":[{"title":"daiquocnguyen/Graph-Transformer","url":"https://github.com/daiquocnguyen/Graph-Transformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/link-prediction-on-collab","task":"Link Prediction","dataset_variant":"COLLAB","rows":1,"metrics":["Hits"],"first_row_in_archive_order":{"model":"GatedGCN-PE","paper":"/paper/benchmarking-graph-neural-networks","metrics":{"Hits":"52.849"},"code_links":[{"title":"graphdeeplearning/benchmarking-gnns","url":"https://github.com/graphdeeplearning/benchmarking-gnns"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/ogbn-arxiv/unimp_appnp_vnode_smooth"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/ogbn-proteins/unimp_cross_feat"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/master/examples/GaAN"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/master/ogb_examples/nodeproppred/ogbn-arxiv"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/graphproppred/ogbg_molpcba"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL"},{"title":"shamim-hussain/egt","url":"https://github.com/shamim-hussain/egt"},{"title":"karl-zhao/benchmarking-gnns-pyg","url":"https://github.com/karl-zhao/benchmarking-gnns-pyg"},{"title":"guillaumejaume/tuto-dl-on-graphs","url":"https://github.com/guillaumejaume/tuto-dl-on-graphs"},{"title":"chenfengzhao/gnnhls","url":"https://github.com/chenfengzhao/gnnhls"},{"title":"yashkotadia/GatedGCN-PATTERN","url":"https://github.com/yashkotadia/GatedGCN-PATTERN"},{"title":"changminwu/expandergnn","url":"https://github.com/changminwu/expandergnn"},{"title":"liketheflower/jimmy_dgl","url":"https://github.com/liketheflower/jimmy_dgl"},{"title":"icml2024357/hombasis-gnn","url":"https://github.com/icml2024357/hombasis-gnn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/panda-expanded-width-aware-message-passing","title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","date":"2024-06-06","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":7,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/strengthening-structural-baselines-for-graph","title":"Strengthening structural baselines for graph classification using Local Topological Profile","date":"2023-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diffwire-inductive-graph-rewiring-via-the","title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","date":"2022-06-15","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/template-based-graph-neural-network-with","title":"Template based Graph Neural Network with Optimal Transport Distances","date":"2022-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graphmae-self-supervised-masked-graph","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","date":"2022-05-22","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/maximum-entropy-weighted-independent-set","title":"Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks","date":"2021-07-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/accurate-learning-of-graph-representations-1","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","date":"2021-02-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/factorizable-graph-convolutional-networks","title":"Factorizable Graph Convolutional Networks","date":"2020-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/wasserstein-embedding-for-graph-learning","title":"Wasserstein Embedding for Graph Learning","date":"2020-06-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/benchmarking-graph-neural-networks","title":"Benchmarking Graph Neural Networks","date":"2020-03-02","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":1,"samples_unverified":22,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/segmented-graph-bert-for-graph-instance","title":"Segmented Graph-Bert for Graph Instance Modeling","date":"2020-02-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-fair-comparison-of-graph-neural-networks-1","title":"A Fair Comparison of Graph Neural Networks for Graph Classification","date":"2019-12-20","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/hierarchical-representation-learning-in-graph","title":"Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling","date":"2019-10-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+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/unsupervised-universal-self-attention-network","title":"Universal Graph Transformer Self-Attention Networks","date":"2019-09-26","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/190910086","title":"Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning","date":"2019-09-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-non-negative-factorization-approach-to-node","title":"A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks","date":"2019-09-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/graph-representation-learning-via-hard-and","title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","date":"2019-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/provably-powerful-graph-networks","title":"Provably Powerful Graph Networks","date":"2019-05-27","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neighborhood-enlargement-in-graph-neural","title":"Mutual Information Maximization in Graph Neural Networks","date":"2019-05-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/graph-u-nets","title":"Graph U-Nets","date":"2019-05-11","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dissecting-graph-neural-networks-on-graph","title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","date":"2019-05-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/understanding-attention-in-graph-neural","title":"Understanding Attention and Generalization in Graph Neural Networks","date":"2019-05-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/capsule-graph-neural-network","title":"Capsule Graph Neural Network","date":"2019-05-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/fast-graph-representation-learning-with","title":"Fast Graph Representation Learning with PyTorch Geometric","date":"2019-03-06","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/how-powerful-are-graph-neural-networks","title":"How Powerful are Graph Neural Networks?","date":"2018-10-01","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/when-work-matters-transforming-classical","title":"When Work Matters: Transforming Classical Network Structures to Graph CNN","date":"2018-07-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hierarchical-graph-representation-learning","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","date":"2018-06-22","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":1,"samples_unverified":19,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-end-to-end-deep-learning-architecture-for","title":"An End-to-End Deep Learning Architecture for Graph Classification","date":"2018-04-29","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/dgcnn-disordered-graph-convolutional-neural","title":"DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model","date":"2017-12-10","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/graph-classification-with-2d-convolutional","title":"Graph Classification with 2D Convolutional Neural Networks","date":"2017-07-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-graph-kernels","title":"Deep Graph Kernels","date":"2015-08-10","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":13,"samples_harvested":93,"samples_ran":30,"samples_unverified":63,"pointer_only_for_licence":18,"papers_with_no_sample_that_ran":2,"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."}