Classic
Coauthor-Physics
Structure
1Graphs
34,493Nodes
247,962Edges
5Classes
8415Node Feature Dim
0.9153Homophily
Coverage
374Results
1Variants
59Papers
- Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
- WWW 2026: VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention WWW 2026
- CORE: Contrastive Masked Feature Reconstruction on Graphs CORE: Contrastive Masked Feature Reconstruction on Graphs
- Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering
- Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations
- Model-Driven Graph Contrastive Learning Model-Driven Graph Contrastive Learning
- ICML 2025: Learn Beneficial Noise as Graph Augmentation Learn Beneficial Noise as Graph Augmentation ICML 2025
- WWW 2025: Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition WWW 2025
- ICLR 2024: Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective ICLR 2024
- Revisiting the Necessity of Graph Learning and Common Graph Benchmarks Revisiting the Necessity of Graph Learning and Common Graph Benchmarks
- 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
- NeurIPS 2024: Distributed-Order Fractional Graph Operating Network Distributed-Order Fractional Graph Operating Network NeurIPS 2024
- KDD 2024: Revisiting Graph Autoencoders as Implicit Contrastive Learners Revisiting Graph Autoencoders as Implicit Contrastive Learners KDD 2024
- Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning
- TMLR 2024: GraphFM: A generalist graph transformer that learns transferable representations across diverse domains GraphFM: A generalist graph transformer that learns transferable representations across diverse domains TMLR 2024
- ICML 2024: How Interpretable Are Interpretable Graph Neural Networks? How Interpretable Are Interpretable Graph Neural Networks? ICML 2024
- NeurIPS 2024: Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision NeurIPS 2024
- ICLR 2024: Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks ICLR 2024
- ICLR 2024: Polynormer: Polynomial-Expressive Graph Transformer in Linear Time Polynormer: Polynomial-Expressive Graph Transformer in Linear Time ICLR 2024
- ICML 2024: Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective ICML 2024
- WWW 2024: Graph Contrastive Learning with Cohesive Subgraph Awareness Graph Contrastive Learning with Cohesive Subgraph Awareness WWW 2024
- Rethinking and Simplifying Bootstrapped Graph Latents Rethinking and Simplifying Bootstrapped Graph Latents
- KDD 2023: Marginal Nodes Matter: Towards Structure Fairness in Graphs Marginal Nodes Matter: Towards Structure Fairness in Graphs KDD 2023
- FedGTA: Topology-aware Averaging for Federated Graph Learning FedGTA: Topology-aware Averaging for Federated Graph Learning
- Frameless Graph Knowledge Distillation Frameless Graph Knowledge Distillation
- Structure-Aware DropEdge Towards Deep Graph Convolutional Networks Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
- ICML 2023: Randomized Schur Complement Views for Graph Contrastive Learning Randomized Schur Complement Views for Graph Contrastive Learning ICML 2023
- Clarify Confused Nodes via Separated Learning Clarify Confused Nodes via Separated Learning
- GIMM: InfoMin-Max for Automated Graph Contrastive Learning GIMM: InfoMin-Max for Automated Graph Contrastive Learning
- ICLR 2023: From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module ICLR 2023
- Graph-based Knowledge Distillation: A survey and experimental evaluation Graph-based Knowledge Distillation: A survey and experimental evaluation
- Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks
- WWW 2023: SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking WWW 2023
- HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption
- Localized Graph Contrastive Learning Localized Graph Contrastive Learning
- ICLR 2022: Latent Graph Inference using Product Manifolds Latent Graph Inference using Product Manifolds ICLR 2022
- AAAI 2022: Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating AAAI 2022
- Unifying Graph Contrastive Learning with Flexible Contextual Scopes Unifying Graph Contrastive Learning with Flexible Contextual Scopes
- Relational Self-Supervised Learning on Graphs Relational Self-Supervised Learning on Graphs
- AAAI 2022: Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learning AAAI 2022
- NeurIPS 2022: NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search NAS-Bench-Graph: Benchmarking Graph Neural Architecture Search NeurIPS 2022
- Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspective Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspective
- KDD 2022: Graph Attention Multi-Layer Perceptron Graph Attention Multi-Layer Perceptron KDD 2022
- ICML 2022: Alternately Optimized Graph Neural Networks Alternately Optimized Graph Neural Networks ICML 2022
- 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
- WWW 2022: PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm WWW 2022
- 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
- Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
- Barlow Graph Auto-Encoder for Unsupervised Network Embedding Barlow Graph Auto-Encoder for Unsupervised Network Embedding
- Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
- KDD 2021: ROD: Reception-aware Online Distillation for Sparse Graphs ROD: Reception-aware Online Distillation for Sparse Graphs KDD 2021
- ICML 2021: Elastic Graph Neural Networks Elastic Graph Neural Networks ICML 2021
- WWW 2021: SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling WWW 2021
- WWW 2020: Graph Contrastive Learning with Adaptive Augmentation Graph Contrastive Learning with Adaptive Augmentation WWW 2020
- GraphMix: Improved Training of GNNs for Semi-Supervised Learning GraphMix: Improved Training of GNNs for Semi-Supervised Learning
- AAAI 2019: Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View AAAI 2019
Node classification on one coauthorship graph, predicting each author’s physics field from paper-keyword features. Evaluated by Accuracy.
Dataset details
Task
Co-authorship graph (Physics) node classification from the “Pitfalls of Graph Neural Network Evaluation” paper. The primary catalog metric is Accuracy.
Data
Co-authorship graph (Physics) node classification from the “Pitfalls of Graph Neural Network Evaluation” paper.
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 ↑ | ACC | F1-Macro | F1-Micro | Normalized AUAC | Normalized AUAC (percentage) | Prediction Acc. | Paper |
|---|---|---|---|---|---|---|---|---|---|
| 1 | GrokFormer | 0.9831
±
0.0018 | — | — | — | — | — | — | |
| 2 | PolyFormer | 0.9808
±
0.0027 | — | — | — | — | — | — | |
| 3 | SGFormer | 0.9796
±
0.0081 | — | — | — | — | — | — | |
| 4 | HopGNN | 0.9786
±
0.0016 | — | — | — | — | — | — | |
| 5 | NAGphormer | 0.9785
±
0.0026 | — | — | — | — | — | — | |
| 6 | GAT | 0.9782
±
0.0028 | — | — | — | — | — | — | |
| 7 | GPRGNN | 0.9777
±
0.0015 | — | — | — | — | — | — | |
| 8 | Specformer | 0.9775
±
0.0053 | — | — | — | — | — | — | |
| 9 | GCN | 0.9774
±
0.0035 | — | — | — | — | — | — | |
| 10 | HiGCN | 0.9765
±
0.0035 | — | — | — | — | — | — | |
| 11 | H2GCN | 0.9764
±
0.0050 | — | — | — | — | — | — | |
| 12 | CPGNN | 0.9761
±
0.0048 | — | — | — | — | — | — | |
| 13 | GraphGPS | 0.9760
±
0.0005 | — | — | — | — | — | — | |
| 14 | JacobiConv | 0.9756
±
0.0028 | — | — | — | — | — | — | |
| 15 | GloGNN | 0.9754
±
0.0053 | — | — | — | — | — | — | |
| 16 | GCN+TS | 0.9744
±
0.0014 | — | — | — | — | — | — | |
| 17 | SAGE | 0.9739
±
0.0018 | — | — | — | — | — | — | |
| 18 | GraphTARIF | 0.9739
±
0.0007 | — | — | — | — | — | — | |
| 19 | FAGCN | 0.9737
±
0.0033 | — | — | — | — | — | — | |
| 20 | BernNet | 0.9736
±
0.0030 | — | — | — | — | — | — | |
| 21 | NAGphormer | 0.9734
±
0.0003 | — | — | — | — | — | — | |
| 22 | GAT | 0.9732
±
0.0006 | — | — | — | — | — | — | |
| 23 | OEPG | 0.9730
±
0.0010 | — | — | — | — | — | — | |
| 24 | Polynormer-r | 0.9727
±
0.0008 | — | — | — | — | — | — | |
| 25 | GAT+T | 0.9726
±
0.0003 | — | — | — | — | — | — | |
| 26 | ChebyNet | 0.9725
±
0.0078 | — | — | — | — | — | — | |
| 27 | GPRGNN | 0.9725
±
0.0013 | — | — | — | — | — | — | |
| 28 | SAGE+T | 0.9723
±
0.0000 | — | — | — | — | — | — | |
| 29 | Polynormer | 0.9722
±
0.0006 | — | — | — | — | — | — | |
| 30 | Exphormer | 0.9720
±
0.0010 | — | — | — | — | — | — | |
| 31 | VecFormer | 0.9717
±
0.0024 | — | — | — | — | — | — | |
| 32 | EXPHORMER + GCN | 0.9716
±
0.0013 | — | — | — | — | — | — | |
| 33 | GraphGPS | 0.9712
±
0.0019 | — | — | — | — | — | — | |
| 34 | ACM-GCN | 0.9709
±
0.0020 | — | — | — | — | — | — | |
| 35 | GGCN | 0.9707
±
0.0005 | — | — | — | — | — | — | |
| 36 | OrderedGNN | 0.9700
±
0.0008 | — | — | — | — | — | — | |
| 37 | DCM | 0.9699
±
0.0044 | — | — | — | — | — | — | |
| 38 | Exphormer | 0.9689
±
0.0009 | — | — | — | — | — | — | |
| 39 | Polynormer | 0.9689
±
0.0006 | — | — | — | — | — | — | |
| 40 | NAGphormer | 0.9686
±
0.0021 | — | — | — | — | — | — | |
| 41 | GPRGNN | 0.9685
±
0.0008 | — | — | — | — | — | — | |
| 42 | GraphFM-NFT | 0.9677
±
0.0012 | — | — | — | — | — | — | |
| 43 | LaplaceGNN | 0.9672
±
0.0011 | — | — | — | — | — | — | |
| 44 | GraphGPS | 0.9671
±
0.0015 | — | — | — | — | — | — | |
| 45 | SPEXPHORMER | 0.9670
±
0.0005 | — | — | — | — | — | — | |
| 46 | GraphFM-MFT | 0.9664
±
0.0017 | — | — | — | — | — | — | |
| 47 | GAT | 0.9663
±
0.0025 | — | — | — | — | — | — | |
| 48 | SGFormer | 0.9663
±
0.0014 | — | — | — | — | — | — | |
| 49 | GIRL | 0.9660
±
0.0000 | — | — | — | — | — | — | |
| 50 | DIFFormer | 0.9660
±
0.0018 | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time