</> Code with Papers by Syntology

Datasets › Cora

Cora

Introduced in Automating the Construction of Internet Portals with Machine Learning1 Jan 2000 archive 2025-07-28

The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words.

Source: https://relational.fit.cvut.cz/dataset/CORA Image Source: https://arxiv.org/abs/1611.08402

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 18 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Node Classification Cora SSP Accuracy 90.16% ± 0.59% Optimization of Graph Neural Networks with Natural... russellizadi/ssp 73 Compare
Node Classification Cora with Public Split: fixed 20 nodes per class OGC Accuracy 86.9% From Cluster Assumption to Graph Convolution:... zhengwang100/ogc_ggcm 36 Compare
Node Classification Cora (0.5%) CPF-ind_APPNP Accuracy 77.3% Extract the Knowledge of Graph Neural Networks and Go... BUPT-GAMMA/CPF 15 Compare
Node Classification Cora (1%) CPF-ind-APPNP Accuracy 80.24% Extract the Knowledge of Graph Neural Networks and Go... BUPT-GAMMA/CPF 15 Compare
Node Classification Cora (3%) CPF-tra-GCNII Accuracy 84.18% Extract the Knowledge of Graph Neural Networks and Go... BUPT-GAMMA/CPF 15 Compare
Link Prediction Cora NESS AUC 98.46% NESS: Node Embeddings from Static SubGraphs AstraZeneca/NESS 13 Compare
Graph Clustering Cora R-GMM-VGAE ACC 76.7 Rethinking Graph Auto-Encoder Models for Attributed... nairouz/R-GAE 9 Compare
Node Classification Cora: fixed 20 node per class DSGCN Accuracy 84.2 Bridging the Gap Between Spectral and Spatial Domains in... balcilar/Spectral-Designed-Graph-Convolutions +1 9 Compare
Node Classification Cora Full-supervised GCNII Accuracy 88.49% Simple and Deep Graph Convolutional Networks chennnM/GCNII +3 9 Compare
Document Classification Cora ACNet Accuracy 83.5% Adaptively Connected Neural Networks wanggrun/Adaptively-Connected-Neural-Networks 6 Compare
Community Detection Cora EdMot NMI 0.4226 EdMot: An Edge Enhancement Approach for Motif-aware... benedekrozemberczki/EdMot +1 2 Compare
Link Prediction Cora (biased evaluation) GraphStar (double weight on positive examples) AP 96.15 Graph Star Net for Generalized Multi-Task Learning graph-star-team/graph_star 2 Compare
Node Classification Cora: fixed 10 node per class CPF-tra-GCNII Accuracy 84.1% Extract the Knowledge of Graph Neural Networks and Go... BUPT-GAMMA/CPF 2 Compare
Node Classification Cora: fixed 5 node per class CPF-tra-APPNP Accuracy 80.26% Extract the Knowledge of Graph Neural Networks and Go... BUPT-GAMMA/CPF 2 Compare
Graph Classification Cora sKNN-LDS Accuracy 72.3 Mutual Information Maximization in Graph Neural Networks CODE-SUBMIT/Graph_Neighborhood_1 +1 1 Compare
Graph structure learning Cora SLAPS Accuracy 73.4 SLAPS: Self-Supervision Improves Structure Learning for... BorealisAI/SLAPS-GNN 1 Compare
Link Prediction Cora (nonstandard variant) GLACE AP 98.52 Gaussian Embedding of Large-scale Attributed Graphs bhagya-hettige/GLACE 1 Compare
Node Classification Cora random partition GraphMix (GCN) Accuracy 82.07 ± 1.17 GraphMix: Improved Training of GNNs for Semi-Supervised Learning vikasverma1077/GraphMix 1 Compare

Papers archive 2025-07-28

30 shown of 117 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 602. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Scale Invariance of Graph Neural Networks 1 1 28 Nov 2024 not harvested
FIT-GNN: Faster Inference Time for GNNs Using Coarsening 1 1 19 Oct 2024 not harvested
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification 1 1 13 Jun 2024 ran 2 of 9 samples (7 unverified)
GSCAN: Graph Stability Clustering for Applications With Noise Using Edge-Aware Excess-of-Mass 1 1 17 Apr 2024 not harvested
Strong Transitivity Relations and Graph Neural Networks 1 1 1 Jan 2024 not harvested
Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures 1 1 28 Dec 2023 not harvested
Contrastive Deep Nonnegative Matrix Factorization for Community Detection 1 1 4 Nov 2023 not harvested
From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited 1 2 24 Sep 2023 not harvested
Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity 3 1 18 Aug 2023 ran 5 of 26 samples (21 unverified)
Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals 1 1 1 Jul 2023 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
The Split Matters: Flat Minima Methods for Improving the Performance of GNNs 1 2 15 Jun 2023 not harvested
Clarify Confused Nodes via Separated Learning 1 1 4 Jun 2023 not harvested
Graph Entropy Minimization for Semi-supervised Node Classification 1 1 31 May 2023 not harvested
NESS: Node Embeddings from Static SubGraphs 1 1 15 Mar 2023 not harvested
Multi-Mask Aggregators for Graph Neural Networks 1 1 24 Nov 2022 not harvested
Beyond Homophily with Graph Echo State Networks 0 1 27 Oct 2022 not harvested
TREE-G: Decision Trees Contesting Graph Neural Networks 1 1 6 Jul 2022 ran 0 of 10 samples (10 unverified)
DiffWire: Inductive Graph Rewiring via the Lovász Bound 2 2 15 Jun 2022 not harvested
GraphMAE: Self-Supervised Masked Graph Autoencoders 3 1 22 May 2022 ran 2 of 3 samples (1 unverified; 3 pointer-only for licence)
Inferring from References with Differences for Semi-Supervised Node Classification on Graphs 1 1 11 Apr 2022 not harvested
How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision 2 1 11 Apr 2022 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
View-Consistent Heterogeneous Network on Graphs With Few Labeled Nodes 1 3 17 Mar 2022 not harvested
Graph Representation Learning Beyond Node and Homophily 1 1 3 Mar 2022 not harvested
PPPNE: Personalized proximity preserved network embedding 0 1 1 Feb 2022 not harvested
Understanding over-squashing and bottlenecks on graphs via curvature 4 1 29 Nov 2021 ran 0 of 5 samples (5 unverified)
CN-Motifs Perceptive Graph Neural Networks 0 1 15 Nov 2021 not harvested
Deeper-GXX: Deepening Arbitrary GNNs 0 1 26 Oct 2021 not harvested
FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping 1 1 21 Oct 2021 not harvested
Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation 1 1 17 Oct 2021 ran 5 of 8 samples (3 unverified; 8 pointer-only for licence)
Neural Link Prediction with Walk Pooling 1 1 8 Oct 2021 not harvested

The full list of 117 is in the JSON twin.

Dataset loaders archive 2025-07-28

pytorch-geometric.readthedocs.io/en/latest/modules/datasets.html#torch_geometric.datasets.Planetoidpyg-team/pytorch_geometricpytorch
docs.dgl.ai/api/python/dgl.data.html#citation-network-datasetdmlc/dglpytorchtfmxnet
graphneural.network/datasets/#citationdanielegrattarola/spektraltf
neo4j.com/docs/graph-data-science-client/current/graph-object/#graph-object-load-coraneo4j/graph-data-science-client

4 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Node ClassificationLink PredictionGraph ClassificationDocument ClassificationNode ClusteringCommunity DetectionGraph ClusteringGraph structure learning

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Graphs

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Cora (weighted evaluation)
  • Cora: fixed 5 node per class
  • Cora: fixed 20 node per class
  • Cora: fixed 10 node per class
  • Cora random partition
  • Cora Full-supervised
  • Cora (nonstandard variant)
  • Cora (biased evaluation)
  • Cora with Public Split: fixed 20 nodes per class
  • Cora (3%)
  • Cora (1%)
  • Cora (0.5%)
  • Cora

13 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections