{"url":"/sota/node-classification-on-pubmed","task":{"name":"Node Classification","url":"/task/node-classification","note":null},"dataset":{"name":"Pubmed","url":"/dataset/pubmed"},"category":"Graphs","categories":["Graphs"],"category_note":null,"description":"**Node Classification** is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.\r\n\r\n**Node Classification** models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like [Cora](/dataset/cora), [Citeseer](/dataset/citeseer), and [Pubmed](/dataset/pubmed), among others, typically using Accuracy and F1.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Fast Graph Representation Learning With PyTorch Geometric](https://arxiv.org/pdf/1903.02428v3.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","Training Split","F1","Validation","Accuracy (%)","F1-Score","Inference Time (ms)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","Training Split":null,"F1":"higher","Validation":null,"Accuracy (%)":"higher","F1-Score":"higher","Inference Time (ms)":"lower"}},"counts":{"rows":70,"rows_with_code":58,"rows_with_paper_page":69,"rows_dated":69,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"NCGCN","metrics":{"Accuracy":"91.64 ± 0.53"},"uses_additional_data":false,"paper_date":"2023-06-04","paper":"/paper/clarify-confused-nodes-through-separated","paper_url":"https://arxiv.org/abs/2306.02285v6","paper_title":"Clarify Confused Nodes via Separated Learning","code":"https://github.com/GISec-Team/NCGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"NCSAGE","metrics":{"Accuracy":"91.55 ± 0.38"},"uses_additional_data":false,"paper_date":"2023-06-04","paper":"/paper/clarify-confused-nodes-through-separated","paper_url":"https://arxiv.org/abs/2306.02285v6","paper_title":"Clarify Confused Nodes via Separated Learning","code":"https://github.com/GISec-Team/NCGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ACMII-Snowball-3","metrics":{"Accuracy":"91.31 ± 0.6"},"uses_additional_data":false,"paper_date":"2021-09-12","paper":"/paper/is-heterophily-a-real-nightmare-for-graph","paper_url":"https://arxiv.org/abs/2109.05641v1","paper_title":"Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"ACM-GCN","metrics":{"Accuracy":"90.74 ± 0.5"},"uses_additional_data":false,"paper_date":"2021-09-12","paper":"/paper/is-heterophily-a-real-nightmare-for-graph","paper_url":"https://arxiv.org/abs/2109.05641v1","paper_title":"Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"Graph-MLP + SAF","metrics":{"Accuracy":"90.64 ± 0.46%"},"uses_additional_data":false,"paper_date":"2023-06-15","paper":"/paper/the-split-matters-flat-minima-methods-for","paper_url":"https://arxiv.org/abs/2306.09121v1","paper_title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","code":"https://github.com/foisunt/fmms-in-gnns","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"ACMII-Snowball-2","metrics":{"Accuracy":"90.56 ± 0.39"},"uses_additional_data":false,"paper_date":"2021-09-12","paper":"/paper/is-heterophily-a-real-nightmare-for-graph","paper_url":"https://arxiv.org/abs/2109.05641v1","paper_title":"Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"NodeNet","metrics":{"Accuracy":"90.21%"},"uses_additional_data":false,"paper_date":"2020-06-16","paper":"/paper/nodenet-a-graph-regularised-neural-network","paper_url":"https://arxiv.org/abs/2006.09022v1","paper_title":"NodeNet: A Graph Regularised Neural Network for Node Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"CNMPGNN","metrics":{"Accuracy":"90.07± 0.43"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/cn-motifs-perceptive-graph-neural-networks","paper_url":"https://ieeexplore.ieee.org/document/9606682","paper_title":"CN-Motifs Perceptive Graph Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"CoLinkDist","metrics":{"Accuracy":"89.58%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"CoLinkDistMLP","metrics":{"Accuracy":"89.53%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":11,"model":"SSP","metrics":{"Accuracy":"89.36 ± 0.57"},"uses_additional_data":false,"paper_date":"2020-08-21","paper":"/paper/optimization-of-graph-neural-networks-with","paper_url":"https://arxiv.org/abs/2008.09624v1","paper_title":"Optimization of Graph Neural Networks with Natural Gradient Descent","code":"https://github.com/russellizadi/ssp","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"3ference","metrics":{"Accuracy":"88.90"},"uses_additional_data":false,"paper_date":"2022-04-11","paper":"/paper/inferring-from-references-with-differences","paper_url":"https://www.mdpi.com/2227-7390/10/8/1262/htm","paper_title":"Inferring from References with Differences for Semi-Supervised Node Classification on Graphs","code":"https://github.com/cf020031308/3ference","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"SplineCNN","metrics":{"Accuracy":"88.88%"},"uses_additional_data":false,"paper_date":"2017-11-24","paper":"/paper/splinecnn-fast-geometric-deep-learning-with","paper_url":"http://arxiv.org/abs/1711.08920v2","paper_title":"SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels","code":"https://github.com/rusty1s/pytorch_geometric","n_code_links":5,"syntology":null},{"rank_in_archive_order":14,"model":"LinkDist","metrics":{"Accuracy":"88.86%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"LinkDistMLP","metrics":{"Accuracy":"88.79%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"GCN + Mixup","metrics":{"Accuracy":"87.9%"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/mixup-for-node-and-graph-classification","paper_url":"https://wangywust.github.io/Paper/2021mix.pdf","paper_title":"Mixup for Node and Graph Classification","code":"https://github.com/vanoracai/MixupForGraph","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"GCN-LPA","metrics":{"Accuracy":"87.8 ± 0.6"},"uses_additional_data":false,"paper_date":"2020-02-17","paper":"/paper/unifying-graph-convolutional-neural-networks-1","paper_url":"https://arxiv.org/abs/2002.06755v1","paper_title":"Unifying Graph Convolutional Neural Networks and Label Propagation","code":"https://github.com/hwwang55/GCN-LPA","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":12,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"CGT","metrics":{"Accuracy":"86.86±0.12"},"uses_additional_data":false,"paper_date":"2023-12-28","paper":"/paper/mitigating-degree-biases-in-message-passing","paper_url":"https://arxiv.org/abs/2312.16788v1","paper_title":"Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures","code":"https://github.com/nslab-cuk/community-aware-graph-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"GRACE","metrics":{"Accuracy":"86.7 ± 0.1"},"uses_additional_data":false,"paper_date":"2020-06-07","paper":"/paper/deep-graph-contrastive-representation","paper_url":"https://arxiv.org/abs/2006.04131v2","paper_title":"Deep Graph Contrastive Representation Learning","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/grace","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":20,"model":"CT-Layer (PE)","metrics":{"Accuracy":"86.07"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/diffwire-inductive-graph-rewiring-via-the","paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","code":"https://github.com/ellisalicante/GraphRewiring-Tutorial","n_code_links":2,"syntology":null},{"rank_in_archive_order":21,"model":"GNN RH-U","metrics":{"Accuracy":"86%"},"uses_additional_data":false,"paper_date":"2019-06-28","paper":"/paper/certifiable-robustness-and-robust-training","paper_url":"https://arxiv.org/abs/1906.12269v1","paper_title":"Certifiable Robustness and Robust Training for Graph Convolutional Networks","code":"https://github.com/danielzuegner/robust-gcn","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"MMA","metrics":{"Accuracy":"86.00%"},"uses_additional_data":false,"paper_date":"2022-11-24","paper":"/paper/multi-mask-aggregators-for-graph-neural","paper_url":"https://openreview.net/forum?id=hZ3b8CskgC","paper_title":"Multi-Mask Aggregators for Graph Neural Networks","code":"https://github.com/asarigun/mma","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"DFNet-ATT","metrics":{"Accuracy":"85.2 ± 0.3"},"uses_additional_data":false,"paper_date":"2019-10-24","paper":"/paper/dfnets-spectral-cnns-for-graphs-with-feedback","paper_url":"https://arxiv.org/abs/1910.10866v5","paper_title":"DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters","code":"https://github.com/wokas36/DFNets","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"GResNet(LoopyNet)","metrics":{"Accuracy":"83.0%"},"uses_additional_data":false,"paper_date":"2019-09-12","paper":"/paper/gresnet-graph-residuals-for-reviving-deep","paper_url":"https://arxiv.org/abs/1909.05729v2","paper_title":"GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation","code":"https://github.com/anonymous-sourcecode/GResNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"PA-GNN","metrics":{"Accuracy":"82.92 ± 0.13"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807558","paper_url":"https://arxiv.org/abs/1908.07558v3","paper_title":"Transferring Robustness for Graph Neural Network Against Poisoning Attacks","code":"https://github.com/tangxianfeng/PA-GNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"GResNet(GAT)","metrics":{"Accuracy":"82.2%"},"uses_additional_data":false,"paper_date":"2019-09-12","paper":"/paper/gresnet-graph-residuals-for-reviving-deep","paper_url":"https://arxiv.org/abs/1909.05729v2","paper_title":"GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation","code":"https://github.com/anonymous-sourcecode/GResNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":27,"model":"TGCL+ResNet","metrics":{"Accuracy":"81.92±0.13"},"uses_additional_data":false,"paper_date":"2021-10-26","paper":"/paper/tackling-oversmoothing-of-gnns-with-1","paper_url":"https://arxiv.org/abs/2110.13798v3","paper_title":"Deeper-GXX: Deepening Arbitrary GNNs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"DSGCN","metrics":{"Accuracy":"81.9%","Training Split":"fixed 20 per class"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"GResNet(GCN)","metrics":{"Accuracy":"81.7%"},"uses_additional_data":false,"paper_date":"2019-09-12","paper":"/paper/gresnet-graph-residuals-for-reviving-deep","paper_url":"https://arxiv.org/abs/1909.05729v2","paper_title":"GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation","code":"https://github.com/anonymous-sourcecode/GResNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":30,"model":"LoopyNet","metrics":{"Accuracy":"81.2%"},"uses_additional_data":false,"paper_date":"2019-09-12","paper":"/paper/gresnet-graph-residuals-for-reviving-deep","paper_url":"https://arxiv.org/abs/1909.05729v2","paper_title":"GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation","code":"https://github.com/anonymous-sourcecode/GResNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"MixHop","metrics":{"Accuracy":"80.8%","Training Split":"20 per node","Validation":"YES"},"uses_additional_data":false,"paper_date":"2019-04-30","paper":"/paper/mixhop-higher-order-graph-convolution","paper_url":"https://arxiv.org/abs/1905.00067v3","paper_title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/mixhop","n_code_links":3,"syntology":null},{"rank_in_archive_order":32,"model":"MTGAE","metrics":{"Accuracy":"80.40%","Training Split":"20 per node","Validation":"YES"},"uses_additional_data":false,"paper_date":"2018-11-07","paper":"/paper/multi-task-graph-autoencoders","paper_url":"http://arxiv.org/abs/1811.02798v1","paper_title":"Multi-Task Graph Autoencoders","code":"https://github.com/vuptran/graph-representation-learning","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"HGCN","metrics":{"Accuracy":"80.3%"},"uses_additional_data":false,"paper_date":"2019-10-28","paper":"/paper/hyperbolic-graph-convolutional-neural","paper_url":"https://arxiv.org/abs/1910.12933v1","paper_title":"Hyperbolic Graph Convolutional Neural Networks","code":"https://github.com/HazyResearch/hgcn","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":34,"model":"Cleora","metrics":{"Accuracy":"80.2"},"uses_additional_data":false,"paper_date":"2021-02-03","paper":"/paper/cleora-a-simple-strong-and-scalable-graph","paper_url":"https://arxiv.org/abs/2102.02302v1","paper_title":"Cleora: A Simple, Strong and Scalable Graph Embedding Scheme","code":"https://github.com/Synerise/cleora","n_code_links":2,"syntology":null},{"rank_in_archive_order":35,"model":"SPF-GCN","metrics":{"Accuracy":"80.0%"},"uses_additional_data":false,"paper_date":"2019-07-02","paper":"/paper/structure-fusion-based-on-graph-convolutional","paper_url":"https://arxiv.org/abs/1907.02586v1","paper_title":"Structure fusion based on graph convolutional networks for semi-supervised classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"JK (Heat Diffusion)","metrics":{"Accuracy":"79.95%"},"uses_additional_data":false,"paper_date":"2019-10-28","paper":"/paper/diffusion-improves-graph-learning-1","paper_url":"https://arxiv.org/abs/1911.05485v6","paper_title":"Diffusion Improves Graph Learning","code":"https://github.com/klicperajo/gdc","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"AdaGCN","metrics":{"Accuracy":"79.76 ± 0.27"},"uses_additional_data":true,"paper_date":"2019-08-14","paper":"/paper/adagcn-adaboosting-graph-convolutional","paper_url":"https://arxiv.org/abs/1908.05081v3","paper_title":"AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models","code":"https://github.com/datake/AdaGCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"APPNP","metrics":{"Accuracy":"79.73 ± 0.31","Validation":"YES"},"uses_additional_data":true,"paper_date":"2018-10-14","paper":"/paper/predict-then-propagate-graph-neural-networks","paper_url":"https://arxiv.org/abs/1810.05997v6","paper_title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/appnp","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"GOCN","metrics":{"Accuracy":"79.7%"},"uses_additional_data":false,"paper_date":"2019-04-26","paper":"/paper/graph-optimized-convolutional-networks","paper_url":"https://arxiv.org/abs/1904.11883v2","paper_title":"Robust Graph Data Learning via Latent Graph Convolutional Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"AGNN-w/o share","metrics":{"Accuracy":"79.7 ± 0.4%"},"uses_additional_data":false,"paper_date":"2019-09-07","paper":"/paper/auto-gnn-neural-architecture-search-of-graph","paper_url":"https://arxiv.org/abs/1909.03184v2","paper_title":"Auto-GNN: Neural Architecture Search of Graph Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":41,"model":"GraphNAS","metrics":{"Accuracy":"79.6 ± 0.4%"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/graphnas-graph-neural-architecture-search","paper_url":"https://arxiv.org/abs/1904.09981v2","paper_title":"GraphNAS: Graph Neural Architecture Search with Reinforcement Learning","code":"https://github.com/GraphNAS/GraphNAS-simple","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"Graph U-Nets","metrics":{"Accuracy":"79.6 ± 0.2%"},"uses_additional_data":false,"paper_date":"2019-05-11","paper":"/paper/graph-u-nets","paper_url":"https://arxiv.org/abs/1905.05178v1","paper_title":"Graph U-Nets","code":"https://github.com/HongyangGao/gunet","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":2}},{"rank_in_archive_order":43,"model":"LGCN sub","metrics":{"Accuracy":"79.5%"},"uses_additional_data":false,"paper_date":"2018-08-12","paper":"/paper/large-scale-learnable-graph-convolutional","paper_url":"http://arxiv.org/abs/1808.03965v1","paper_title":"Large-Scale Learnable Graph Convolutional Networks","code":"https://github.com/divelab/lgcn","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"N-GCN","metrics":{"Accuracy":"79.5%"},"uses_additional_data":false,"paper_date":"2018-02-24","paper":"/paper/n-gcn-multi-scale-graph-convolution-for-semi","paper_url":"http://arxiv.org/abs/1802.08888v1","paper_title":"N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classification","code":"https://github.com/samihaija/mixhop","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"DifNet","metrics":{"Accuracy":"79.5%"},"uses_additional_data":false,"paper_date":"2020-01-22","paper":"/paper/get-rid-of-suspended-animation-problem-deep","paper_url":"https://arxiv.org/abs/2001.07922v1","paper_title":"Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification","code":"https://github.com/jwzhanggy/DifNet","n_code_links":2,"syntology":null},{"rank_in_archive_order":46,"model":"alpha-LoNGAE","metrics":{"Accuracy":"79.40%"},"uses_additional_data":false,"paper_date":"2018-02-23","paper":"/paper/learning-to-make-predictions-on-graphs-with","paper_url":"http://arxiv.org/abs/1802.08352v2","paper_title":"Learning to Make Predictions on Graphs with Autoencoders","code":"https://github.com/vuptran/graph-representation-learning","n_code_links":2,"syntology":null},{"rank_in_archive_order":47,"model":"APPNP","metrics":{"Accuracy":"79.4 ± 2.2"},"uses_additional_data":false,"paper_date":"2019-03-06","paper":"/paper/fast-graph-representation-learning-with","paper_url":"http://arxiv.org/abs/1903.02428v3","paper_title":"Fast Graph Representation Learning with PyTorch Geometric","code":"https://github.com/rusty1s/pytorch_geometric","n_code_links":6,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"Graphite","metrics":{"Accuracy":"79.3 ± 0.03"},"uses_additional_data":false,"paper_date":"2018-03-28","paper":"/paper/graphite-iterative-generative-modeling-of","paper_url":"https://arxiv.org/abs/1803.10459v4","paper_title":"Graphite: Iterative Generative Modeling of Graphs","code":"https://github.com/ermongroup/graphite","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"SF-GCN","metrics":{"Accuracy":"79.3%"},"uses_additional_data":false,"paper_date":"2019-07-02","paper":"/paper/structure-fusion-based-on-graph-convolutional","paper_url":"https://arxiv.org/abs/1907.02586v1","paper_title":"Structure fusion based on graph convolutional networks for semi-supervised classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"Graph-Bert","metrics":{"Accuracy":"79.3%"},"uses_additional_data":false,"paper_date":"2020-01-15","paper":"/paper/graph-bert-only-attention-is-needed-for","paper_url":"https://arxiv.org/abs/2001.05140v2","paper_title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","code":"https://github.com/jwzhanggy/Graph-Bert","n_code_links":2,"syntology":null},{"rank_in_archive_order":51,"model":"GWNN","metrics":{"Accuracy":"79.1%"},"uses_additional_data":false,"paper_date":"2019-04-12","paper":"/paper/graph-wavelet-neural-network-1","paper_url":"http://arxiv.org/abs/1904.07785v1","paper_title":"Graph Wavelet Neural Network","code":"https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"SDRF","metrics":{"Accuracy":"79.10±0.11"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/understanding-over-squashing-and-bottlenecks-1","paper_url":"https://arxiv.org/abs/2111.14522v3","paper_title":"Understanding over-squashing and bottlenecks on graphs via curvature","code":"https://github.com/jctops/understanding-oversquashing","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":53,"model":"GAT","metrics":{"Accuracy":"79.0 ± 0.3%","F1-Score":"79.0","Training Split":"fixed 20 per node","Validation":"YES"},"uses_additional_data":false,"paper_date":"2017-10-30","paper":"/paper/graph-attention-networks","paper_url":"http://arxiv.org/abs/1710.10903v3","paper_title":"Graph Attention Networks","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":93,"syntology":{"n_ran":50,"n_unverified":56,"n_samples":106,"n_pointer_only_licence":43}},{"rank_in_archive_order":54,"model":"GCN","metrics":{"Accuracy":"79.0"},"uses_additional_data":false,"paper_date":"2016-09-09","paper":"/paper/semi-supervised-classification-with-graph","paper_url":"http://arxiv.org/abs/1609.02907v4","paper_title":"Semi-Supervised Classification with Graph Convolutional Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gcn","n_code_links":55,"syntology":{"n_ran":31,"n_unverified":27,"n_samples":58,"n_pointer_only_licence":22}},{"rank_in_archive_order":55,"model":"Caps2NE","metrics":{"Accuracy":"78.45%"},"uses_additional_data":false,"paper_date":"2019-11-12","paper":"/paper/a-capsule-network-based-model-for-learning","paper_url":"https://arxiv.org/abs/1911.04822v2","paper_title":"A Capsule Network-based Model for Learning Node Embeddings","code":"https://github.com/daiquocnguyen/Caps2NE","n_code_links":1,"syntology":null},{"rank_in_archive_order":56,"model":"G3NN","metrics":{"Accuracy":"78.4%","Training Split":"20 per node with early stopping set","Validation":"YES"},"uses_additional_data":false,"paper_date":"2019-05-26","paper":"/paper/a-flexible-generative-framework-for-graph","paper_url":"https://arxiv.org/abs/1905.10769v2","paper_title":"A Flexible Generative Framework for Graph-based Semi-supervised Learning","code":"https://github.com/jiaqima/G3NN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":57,"model":"TREE-G","metrics":{"Accuracy":"78.0"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/graph-trees-with-attention","paper_url":"https://arxiv.org/abs/2207.02760v5","paper_title":"TREE-G: Decision Trees Contesting Graph Neural Networks","code":"https://github.com/mayabechlerspeicher/tree-g","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":58,"model":"GCN + AdaGraph (AG)","metrics":{"Accuracy":"77.4 ± 0.2"},"uses_additional_data":false,"paper_date":"2019-09-07","paper":"/paper/measuring-and-relieving-the-over-smoothing","paper_url":"https://arxiv.org/abs/1909.03211v2","paper_title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":59,"model":"Graph InfoClust (GIC)","metrics":{"Accuracy":"77.4 ± 1.9"},"uses_additional_data":false,"paper_date":"2020-09-15","paper":"/paper/graph-infoclust-leveraging-cluster-level-node","paper_url":"https://arxiv.org/abs/2009.06946v1","paper_title":"Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning","code":"https://github.com/cmavro/Graph-InfoClust-GIC","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":60,"model":"GraphStar","metrics":{"Accuracy":"77.2%"},"uses_additional_data":false,"paper_date":"2019-06-21","paper":"/paper/graph-star-net-for-generalized-multi-task-1","paper_url":"https://arxiv.org/abs/1906.12330v1","paper_title":"Graph Star Net for Generalized Multi-Task Learning","code":"https://github.com/graph-star-team/graph_star","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":61,"model":"Planetoid*","metrics":{"Accuracy":"77.2%"},"uses_additional_data":false,"paper_date":"2016-03-29","paper":"/paper/revisiting-semi-supervised-learning-with","paper_url":"http://arxiv.org/abs/1603.08861v2","paper_title":"Revisiting Semi-Supervised Learning with Graph Embeddings","code":"https://github.com/tkipf/gcn","n_code_links":26,"syntology":{"n_ran":15,"n_unverified":13,"n_samples":28,"n_pointer_only_licence":4}},{"rank_in_archive_order":62,"model":"DGI","metrics":{"Accuracy":"76.8 ± 0.6%"},"uses_additional_data":false,"paper_date":"2018-09-27","paper":"/paper/deep-graph-infomax","paper_url":"http://arxiv.org/abs/1809.10341v2","paper_title":"Deep Graph Infomax","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/dgi","n_code_links":11,"syntology":{"n_ran":24,"n_unverified":11,"n_samples":35,"n_pointer_only_licence":9}},{"rank_in_archive_order":63,"model":"GLNN","metrics":{"Accuracy":"75.42 ± 2.31"},"uses_additional_data":false,"paper_date":"2021-10-17","paper":"/paper/graph-less-neural-networks-teaching-old-mlps-1","paper_url":"https://arxiv.org/abs/2110.08727v2","paper_title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","code":"https://github.com/snap-research/graphless-neural-networks","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":64,"model":"ChebNet","metrics":{"Accuracy":"74.4%"},"uses_additional_data":false,"paper_date":"2016-06-30","paper":"/paper/convolutional-neural-networks-on-graphs-with","paper_url":"http://arxiv.org/abs/1606.09375v3","paper_title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","code":"https://github.com/mdeff/cnn_graph","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":2}},{"rank_in_archive_order":65,"model":"CT-Layer","metrics":{"Accuracy":"68.19"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/diffwire-inductive-graph-rewiring-via-the","paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","code":"https://github.com/ellisalicante/GraphRewiring-Tutorial","n_code_links":2,"syntology":null},{"rank_in_archive_order":66,"model":"DANMF","metrics":{"Accuracy":"63.93%"},"uses_additional_data":false,"paper_date":"2018-10-22","paper":"/paper/deep-autoencoder-like-nonnegative-matrix","paper_url":"https://dl.acm.org/citation.cfm?id=3271697","paper_title":"Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection","code":"https://github.com/benedekrozemberczki/karateclub","n_code_links":2,"syntology":null},{"rank_in_archive_order":67,"model":"PairE","metrics":{"F1":"88.57"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/graph-representation-learning-beyond-node-and","paper_url":"https://arxiv.org/abs/2203.01564v1","paper_title":"Graph Representation Learning Beyond Node and Homophily","code":"https://github.com/syvail/PairE-Graph-Representation-Learning-Beyond-Node-and-Homophily","n_code_links":1,"syntology":null},{"rank_in_archive_order":68,"model":"ClusterGCN","metrics":{"F1":"79.9"},"uses_additional_data":false,"paper_date":"2019-05-20","paper":"/paper/cluster-gcn-an-efficient-algorithm-for","paper_url":"https://arxiv.org/abs/1905.07953v2","paper_title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","code":"https://github.com/google-research/google-research","n_code_links":6,"syntology":null},{"rank_in_archive_order":69,"model":"PathNet","metrics":{"Accuracy (%)":"88.92"},"uses_additional_data":false,"paper_date":"2022-07-20","paper":"/paper/beyond-homophily-structure-aware-path","paper_url":"https://www.ijcai.org/proceedings/2022/310","paper_title":"Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network","code":"https://github.com/zjunet/PathNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":70,"model":"FIT-GNN","metrics":{"Inference Time (ms)":"0.0018"},"uses_additional_data":false,"paper_date":"2024-10-19","paper":"/paper/faster-inference-time-for-gnns-using","paper_url":"https://arxiv.org/abs/2410.15001v2","paper_title":"FIT-GNN: Faster Inference Time for GNNs Using Coarsening","code":"https://github.com/Roy-Shubhajit/FIT-GNN","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":26,"rows_with_any_sample_ran":15,"distinct_papers_with_graph_line":23,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":143,"n_unverified":185,"n_samples":328,"n_pointer_only_licence":96,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":143,"n_unverified":188,"n_samples":331,"n_pointer_only_licence":99,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}