Classic
WikiCS
Structure
1Graphs
11,701Nodes
216,123Edges
10Classes
300Node Feature Dim
0.74Homophily
Coverage
433Results
1Variants
55Papers
- Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
- Adaptive Negative Scheduling for Graph Contrastive Learning Adaptive Negative Scheduling for Graph Contrastive Learning
- ICLR 2026: Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors ICLR 2026
- CO-EVOLVE: Bidirectional Co-Evolution of Graph Structure and Semantics for Heterophilous Learning CO-EVOLVE: Bidirectional Co-Evolution of Graph Structure and Semantics for Heterophilous Learning
- Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
- Energy-Balanced Hyperspherical Graph Representation Learning via Structural Binding and Entropic Dispersion Energy-Balanced Hyperspherical Graph Representation Learning via Structural Binding and Entropic Dispersion
- ICML 2025: View Space: Learning Representation across Arbitrary Graphs View Space: Learning Representation across Arbitrary Graphs ICML 2025
- LoG 2025: Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization? Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization? LoG 2025
- NeurIPS 2025: Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models NeurIPS 2025
- Toward General Digraph Contrastive Learning: A Dual Spatial Perspective Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
- FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
- From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
- KDD 2025: Quantizing Text-attributed Graphs for Semantic-Structural Integration Quantizing Text-attributed Graphs for Semantic-Structural Integration KDD 2025
- Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations
- KDD 2025: Discrepancy-Aware Graph Mask Auto-Encoder Discrepancy-Aware Graph Mask Auto-Encoder KDD 2025
- Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
- NeurIPS 2025: Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement NeurIPS 2025
- IJCAI 2025: Rethinking Graph Contrastive Learning through Relative Similarity Preservation Rethinking Graph Contrastive Learning through Relative Similarity Preservation IJCAI 2025
- ICML 2025: Toward Data-centric Directed Graph Learning: An Entropy-driven Approach Toward Data-centric Directed Graph Learning: An Entropy-driven Approach ICML 2025
- LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
- ICML 2025: Beyond Message Passing: Neural Graph Pattern Machine Beyond Message Passing: Neural Graph Pattern Machine ICML 2025
- PyG-SSL: A Graph Self-Supervised Learning Toolkit PyG-SSL: A Graph Self-Supervised Learning Toolkit
- Scale-aware Message Passing For Graph Node Classification Scale-aware Message Passing For Graph Node Classification
- ICML 2024: GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers ICML 2024
- NeurIPS 2024: Even Sparser Graph Transformers Even Sparser Graph Transformers NeurIPS 2024
- ICML 2024: Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms ICML 2024
- Negative-Free Self-Supervised Gaussian Embedding of Graphs Negative-Free Self-Supervised Gaussian Embedding of Graphs
- Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning
- UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks
- From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
- NeurIPS 2024: Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights NeurIPS 2024
- ICLR 2024: Fully-inductive Node Classification on Arbitrary Graphs Fully-inductive Node Classification on Arbitrary Graphs ICLR 2024
- Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models
- ICLR 2024: Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning ICLR 2024
- E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification
- TMLR 2024: Contextualized Messages Boost Graph Representations Contextualized Messages Boost Graph Representations TMLR 2024
- ICLR 2024: Polynormer: Polynomial-Expressive Graph Transformer in Linear Time Polynormer: Polynomial-Expressive Graph Transformer in Linear Time ICLR 2024
- AAAI 2024: Rethinking Graph Masked Autoencoders through Alignment and Uniformity Rethinking Graph Masked Autoencoders through Alignment and Uniformity AAAI 2024
- IJCAI 2024: Efficient Tuning and Inference for Large Language Models on Textual Graphs Efficient Tuning and Inference for Large Language Models on Textual Graphs IJCAI 2024
- LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
- Rethinking and Simplifying Bootstrapped Graph Latents Rethinking and Simplifying Bootstrapped Graph Latents
- ICLR 2023: Label-free Node Classification on Graphs with Large Language Models (LLMs) Label-free Node Classification on Graphs with Large Language Models (LLMs) ICLR 2023
- JMLR 2023: GNNBenchmark GNNBenchmark JMLR 2023
- Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective
- Graph Soft-Contrastive Learning via Neighborhood Ranking Graph Soft-Contrastive Learning via Neighborhood Ranking
- Relational Self-Supervised Learning on Graphs Relational Self-Supervised Learning on Graphs
- ICML 2022: Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning ICML 2022
- Augmentation-Free Graph Contrastive Learning with Performance Guarantee Augmentation-Free Graph Contrastive Learning with Performance Guarantee
- Graph Representation Learning via Aggregation Enhancement Graph Representation Learning via Aggregation Enhancement
- Learning Graph Augmentations to Learn Graph Representations Learning Graph Augmentations to Learn Graph Representations
- AAAI 2021: Augmentation-Free Self-Supervised Learning on Graphs Augmentation-Free Self-Supervised Learning on Graphs AAAI 2021
- Barlow Graph Auto-Encoder for Unsupervised Network Embedding Barlow Graph Auto-Encoder for Unsupervised Network Embedding
- WWW 2021: Graph Communal Contrastive Learning Graph Communal Contrastive Learning WWW 2021
- Graph Barlow Twins: A self-supervised representation learning framework for graphs Graph Barlow Twins: A self-supervised representation learning framework for graphs
- ICLR 2021: Large-Scale Representation Learning on Graphs via Bootstrapping Large-Scale Representation Learning on Graphs via Bootstrapping ICLR 2021
10-class node classification on a Wikipedia hyperlink graph, predicting each article’s computer-science category from text-derived features. Evaluated by Accuracy.
Dataset details
Task
Wikipedia-based node classification (10 classes) with 20 train splits. The primary catalog metric is Accuracy.
Data
Wikipedia-based node classification (10 classes) with 20 train splits. The cataloged artifact reports 1 graphs, 10 target classes or tasks.
Features
The representation follows the cited PyG loader or benchmark release. Node and edge fields are dataset-specific; preprocessing, graph direction, and any feature normalization must be kept fixed when reproducing a result.
Splits and evaluation
The catalog records these protocols or variants: Standard split. Evaluation uses Accuracy (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
The same short dataset name is used for incompatible processed artifacts and split protocols. Report the loader/version, directedness, feature preprocessing, and exact masks; transductive results should not be described as inductive.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | Accuracy ↑ | F1 | Fidelity | Macro-F1 | Micro-F1 | Paper |
|---|---|---|---|---|---|---|---|
| 1 | GCN | 0.9302
±
0.0011 | — | — | — | — | |
| 2 | RSE + RGCN (70b) | 0.8852
±
0.0019 | — | — | — | — | |
| 3 | LEMP+T | 0.8825 | — | — | — | — | |
| 4 | RevGAT+T | 0.8824 | — | — | — | — | |
| 5 | SAGE+T | 0.8823 | — | — | — | — | |
| 6 | RSE + SeHGNN (70b) | 0.8796
±
0.0020 | — | — | — | — | |
| 7 | GraphSSR | 0.8793 | — | — | — | — | |
| 8 | Jacobi | 0.8778 | — | — | — | — | |
| 9 | SAGE | 0.8771 | — | — | — | — | |
| 10 | RSE + UniMP (70b) | 0.8769
±
0.0018 | — | — | — | — | |
| 11 | GPR | 0.8755 | — | — | — | — | |
| 12 | APPNP | 0.8754 | — | — | — | — | |
| 13 | RSE + HAN (70b) | 0.8749
±
0.0015 | — | — | — | — | |
| 14 | LEMP | 0.8729 | — | — | — | — | |
| 15 | GBK | 0.8723 | — | — | — | — | |
| 16 | GCN | 0.8700 | — | — | — | — | |
| 17 | Graph-R1 | 0.8689 | — | — | — | — | |
| 18 | OGNN | 0.8684 | — | — | — | — | |
| 19 | GCNII | 0.8674 | — | — | — | — | |
| 20 | RevGAT | 0.8665 | — | — | — | — | |
| 21 | H2GCN | 0.8660 | — | — | — | — | |
| 22 | FAGCN | 0.8655 | — | — | — | — | |
| 23 | Disam | 0.8651 | — | — | — | — | |
| 24 | JKNet | 0.8629 | — | — | — | — | |
| 25 | MPNN | 0.8621
±
0.0039 | — | — | — | — | |
| 26 | SATA | 0.8602 | — | — | — | — | |
| 27 | MLP+LLM_features | 0.8597 | — | — | — | — | |
| 28 | Cheby | 0.8597 | — | — | — | — | |
| 29 | BORF | 0.8589
±
0.0028 | — | — | — | — | |
| 30 | GrokFormer | 0.8557
±
0.0065 | — | — | — | — | |
| 31 | CO-EVOLVE | 0.8535 | — | — | — | — | |
| 32 | GAT | 0.8533 | — | — | — | — | |
| 33 | Specformer | 0.8515
±
0.0063 | — | — | — | — | |
| 34 | HopGNN | 0.8473
±
0.0059 | — | — | — | — | |
| 35 | PromptGFM | 0.8466 | — | — | — | — | |
| 36 | SPEXPHORMER | 0.8453
±
0.0015 | — | — | — | — | |
| 37 | TAPE | 0.8444 | — | — | — | — | |
| 38 | VCR-Graphormer | 0.8432
±
0.0001 | — | — | — | — | |
| 39 | UniMP | 0.8429
±
0.0023 | — | — | — | — | |
| 40 | JacobiConv | 0.8413
±
0.0049 | — | — | — | — | |
| 41 | Graph-Mamba | 0.8407
±
0.0076 | — | — | — | — | |
| 42 | STAG + Linear Probing | 0.8405
±
0.0578 | — | — | — | — | |
| 43 | UniFilter | 0.8400
±
0.0026 | — | — | — | — | |
| 44 | CoBFormer | 0.8395
±
0.0028 | — | — | — | — | |
| 45 | MPNN+VN | 0.8367
±
0.0066 | — | — | — | — | |
| 46 | PolyFormer | 0.8362
±
0.0017 | — | — | — | — | |
| 47 | BernNet | 0.8356
±
0.0061 | — | — | — | — | |
| 48 | STAG + Prompt Tuning | 0.8355
±
0.0594 | — | — | — | — | |
| 49 | H2GCN | 0.8345
±
0.0026 | — | — | — | — | |
| 50 | NAGphormer | 0.8341
±
0.0034 | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time