Wiki-CS is a Wikipedia-based dataset for benchmarking Graph Neural Networks. The dataset is constructed from Wikipedia categories, specifically 10 classes corresponding to branches of computer science, with very high connectivity. The node features are derived from the text of the corresponding articles. They were calculated as the average of pretrained GloVe word embeddings (Pennington et al., 2014), resulting in 300-dimensional node features.
The dataset has 11,701 nodes and 216,123 edges.
Source: Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks
Image Source: https://arxiv.org/pdf/2007.02901v1.pdf
Variants: Wiki-CS
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Node Classification | ScaleNet | Scale Invariance of Graph Neural … | 2024-11-28 |
| Node Classification | CGT | Mitigating Degree Biases in Message … | 2023-12-28 |
| Node Classification | GraphSAGE | Half-Hop: A graph upsampling approach … | 2023-08-17 |
| Node Classification | HH-GraphSAGE | Half-Hop: A graph upsampling approach … | 2023-08-17 |
| Node Classification | HH-GCN | Half-Hop: A graph upsampling approach … | 2023-08-17 |
| Node Classification | GCN | Half-Hop: A graph upsampling approach … | 2023-08-17 |
Recent papers with results on this dataset: