Datasets › Wiki Squirrel

Wiki Squirrel (Wikipedia Squirrel)

Introduced by Benedek Rozemberczki et al. in Multi-scale Attributed Node Embedding28 Sep 2019 archive 2025-07-28

The data was collected from the English Wikipedia (December 2018). These datasets represent page-page networks on specific topics (chameleons, crocodiles and squirrels). Nodes represent articles and edges are mutual links between them. The edges csv files contain the edges - nodes are indexed from 0. The features json files contain the features of articles - each key is a page id, and node features are given as lists. The presence of a feature in the feature list means that an informative noun appeared in the text of the Wikipedia article. The target csv contains the node identifiers and the average monthly traffic between October 2017 and November 2018 for each page. For each page-page network we listed the number of nodes an edges with some other descriptive statistics.

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 Squirrel FaberNet Accuracy 76.71±1.92 HoloNets: Spectral Convolutions do extend to Directed Graphs ChristianKoke/HoloNets 59 Compare

Papers archive 2025-07-28

30 shown of 44 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 208. 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
Heterophilic Graph Neural Networks Optimization with Causal Message-passing 0 1 21 Nov 2024 not harvested
Improving Graph Neural Networks by Learning Continuous Edge Directions 1 1 18 Oct 2024 not harvested
The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs 1 1 18 Jun 2024 not harvested
Graph Neural Reaction Diffusion Models 0 1 16 Jun 2024 not harvested
Transfer Entropy in Graph Convolutional Neural Networks 1 1 8 Jun 2024 not harvested
Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs 1 1 31 May 2024 not harvested
Heterophilous Distribution Propagation for Graph Neural Networks 0 1 31 May 2024 not harvested
Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network 1 1 26 Mar 2024 not harvested
Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks 0 1 27 Dec 2023 not harvested
GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy 0 1 15 Dec 2023 not harvested
CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph 1 1 14 Dec 2023 not harvested
Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification 0 1 7 Dec 2023 not harvested
SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning 0 1 17 Oct 2023 not harvested
HoloNets: Spectral Convolutions do extend to Directed Graphs 1 1 3 Oct 2023 ran 4 of 5 samples (1 unverified)
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)
Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters 1 1 29 Jun 2023 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Self-attention Dual Embedding for Graphs with Heterophily 0 1 28 May 2023 not harvested
Edge Directionality Improves Learning on Heterophilic Graphs 1 1 17 May 2023 ran 3 of 5 samples (2 unverified)
GCNH: A Simple Method For Representation Learning On Heterophilous Graphs 1 1 21 Apr 2023 not harvested
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing 1 1 3 Feb 2023 ran 1 of 10 samples (9 unverified)
Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach 0 1 20 Nov 2022 not harvested
Beyond Homophily with Graph Echo State Networks 0 1 27 Oct 2022 not harvested
Revisiting Heterophily For Graph Neural Networks 1 8 14 Oct 2022 ran 2 of 7 samples (5 unverified)
Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach 0 1 17 Sep 2022 not harvested
Sheaf Neural Networks with Connection Laplacians 1 1 17 Jun 2022 not harvested
Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering 0 1 6 Jun 2022 not harvested
Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing 0 1 30 May 2022 not harvested
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)
Understanding over-squashing and bottlenecks on graphs via curvature 4 1 29 Nov 2021 ran 0 of 5 samples (5 unverified)

The full list of 44 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

GNU

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Squirrel
  • Wiki Squirrel

2 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