Datasets › Cora (48%/32%/20% fixed splits)

Cora (48%/32%/20% fixed splits)

Introduced by Hongbin Pei et al. in Geom-GCN: Geometric Graph Convolutional Networks13 Feb 2020 archive 2025-07-28

Node classification on Cora with the fixed 48%/32%/20% splits provided by Geom-GCN.

Benchmarks archive 2025-07-28

All 1 leaderboard 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 (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 88.5 ± 1.8 Non-Local Graph Neural Networks divelab/Non-Local-GNN 26 Compare

Papers archive 2025-07-28

15 shown of 15 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 15. 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
Addressing Heterophily in Node Classification with Graph Echo State Networks 1 1 14 May 2023 not harvested
GREAD: Graph Neural Reaction-Diffusion Networks 1 1 25 Nov 2022 ran 3 of 10 samples (7 unverified; 3 pointer-only for licence)
Revisiting Heterophily For Graph Neural Networks 1 7 14 Oct 2022 ran 2 of 7 samples (5 unverified)
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily 1 2 15 May 2022 not harvested
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs 1 3 9 Feb 2022 ran 0 of 1 samples (1 unverified)
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods 5 1 27 Oct 2021 ran 7 of 21 samples (14 unverified; 4 pointer-only for licence)
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns 1 1 11 Jun 2021 ran 1 of 12 samples (11 unverified)
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks 1 1 12 Feb 2021 not harvested
Beyond Low-frequency Information in Graph Convolutional Networks 1 1 4 Jan 2021 not harvested
Simple and Deep Graph Convolutional Networks 4 1 4 Jul 2020 ran 5 of 7 samples (2 unverified; 4 pointer-only for licence)
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs 4 1 20 Jun 2020 ran 13 of 21 samples (8 unverified; 6 pointer-only for licence)
Adaptive Universal Generalized PageRank Graph Neural Network 1 1 14 Jun 2020 ran 0 of 2 samples (2 unverified; 2 pointer-only for licence)
Non-Local Graph Neural Networks 1 3 29 May 2020 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
Geom-GCN: Geometric Graph Convolutional Networks 4 1 13 Feb 2020 ran 7 of 7 samples (0 unverified; 7 pointer-only for licence)
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing 3 1 30 Apr 2019 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Cora (48%/32%/20% fixed splits)

1 variant name, 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