Classic
PPI
Structure
20Graphs
2,245Nodes
61,318Edges
121Classes
50Node Feature Dim
Coverage
310Results
1Variants
55Papers
- GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
- Wide & Deep Learning for Node Classification Wide & Deep Learning for Node Classification
- Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs
- TMLR 2024: Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study Extending Graph Condensation to Multi-Label Datasets: A Benchmark Study TMLR 2024
- TMLR 2024: Disentangled and Self-Explainable Node Representation Learning Disentangled and Self-Explainable Node Representation Learning TMLR 2024
- Disentangled Generative Graph Representation Learning Disentangled Generative Graph Representation Learning
- ICLR 2024: Graph Neural Networks Gone Hogwild Graph Neural Networks Gone Hogwild ICLR 2024
- Subgraph-level Universal Prompt Tuning Subgraph-level Universal Prompt Tuning
- UGMAE: A Unified Framework for Graph Masked Autoencoders UGMAE: A Unified Framework for Graph Masked Autoencoders
- AAAI 2024: Rethinking Graph Masked Autoencoders through Alignment and Uniformity Rethinking Graph Masked Autoencoders through Alignment and Uniformity AAAI 2024
- Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation Shared Growth of Graph Neural Networks via Prompted Free-direction Knowledge Distillation
- ICLR 2023: LMC: Fast Training of GNNs via subgraph-wise sampling with Provable Convergence LMC: Fast Training of GNNs via subgraph-wise sampling with Provable Convergence ICLR 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
- Relational Self-Supervised Learning on Graphs Relational Self-Supervised Learning on Graphs
- ICLR 2022: Learning Hierarchical Protein Representations via Complete 3D Graph Networks Learning Hierarchical Protein Representations via Complete 3D Graph Networks ICLR 2022
- Generative Subgraph Contrast for Self-Supervised Graph Representation Learning Generative Subgraph Contrast for Self-Supervised Graph Representation Learning
- ICML 2022: Optimization-Induced Graph Implicit Nonlinear Diffusion Optimization-Induced Graph Implicit Nonlinear Diffusion ICML 2022
- KDD 2022: FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks KDD 2022
- KDD 2022: Graph Attention Multi-Layer Perceptron Graph Attention Multi-Layer Perceptron KDD 2022
- KDD 2022: GraphMAE: Self-Supervised Masked Graph Autoencoders GraphMAE: Self-Supervised Masked Graph Autoencoders KDD 2022
- ICML 2022: Self-Supervised Representation Learning via Latent Graph Prediction Self-Supervised Representation Learning via Latent Graph Prediction ICML 2022
- ICML 2022: Graph-Coupled Oscillator Networks Graph-Coupled Oscillator Networks ICML 2022
- TMLR 2022: Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings TMLR 2022
- Graph Representation Learning via Aggregation Enhancement Graph Representation Learning via Aggregation Enhancement
- Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations
- On Representation Knowledge Distillation for Graph Neural Networks On Representation Knowledge Distillation for Graph Neural Networks
- NeurIPS 2021: VQ-GNN: A Universal Framework to Scale-up Graph Neural Networks using Vector Quantization VQ-GNN: A Universal Framework to Scale-up Graph Neural Networks using Vector Quantization NeurIPS 2021
- Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks
- Graph Barlow Twins: A self-supervised representation learning framework for graphs Graph Barlow Twins: A self-supervised representation learning framework for graphs
- Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced Training Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced Training
- Search to aggregate neighborhood for graph neural network Search to aggregate neighborhood for graph neural network
- Sampling methods for efficient training of graph convolutional networks: A survey Sampling methods for efficient training of graph convolutional networks: A survey
- WWW 2021: CogDL: A Comprehensive Library for Graph Deep Learning CogDL: A Comprehensive Library for Graph Deep Learning WWW 2021
- Graph Self-Supervised Learning: A Survey Graph Self-Supervised Learning: A Survey
- ICLR 2021: Large-Scale Representation Learning on Graphs via Bootstrapping Large-Scale Representation Learning on Graphs via Bootstrapping ICLR 2021
- Learning to Drop: Robust Graph Neural Network via Topological Denoising Learning to Drop: Robust Graph Neural Network via Topological Denoising
- Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
- Hierarchical message-passing graph neural networks Hierarchical message-passing graph neural networks
- Deep Graph Contrastive Representation Learning Deep Graph Contrastive Representation Learning
- SIGN: Scalable Inception Graph Neural Networks SIGN: Scalable Inception Graph Neural Networks
- L$^2$-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks L$^2$-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
- Distilling Knowledge from Graph Convolutional Networks Distilling Knowledge from Graph Convolutional Networks
- WWW 2020: Graph Representation Learning via Graphical Mutual Information Maximization Graph Representation Learning via Graphical Mutual Information Maximization WWW 2020
- DeepGCNs: Making GCNs Go as Deep as CNNs DeepGCNs: Making GCNs Go as Deep as CNNs
- ICLR 2019: GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding ICLR 2019
- Auto-GNN: Neural Architecture Search of Graph Neural Networks Auto-GNN: Neural Architecture Search of Graph Neural Networks
- ICLR 2019: GraphSAINT: Graph Sampling Based Inductive Learning Method GraphSAINT: Graph Sampling Based Inductive Learning Method ICLR 2019
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
- KDD 2019: Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks KDD 2019
- Graph Neural Networks With Convolutional ARMA Filters Graph Neural Networks With Convolutional ARMA Filters
- A Comprehensive Survey on Graph Neural Networks A Comprehensive Survey on Graph Neural Networks
- Deep Learning on Graphs: A Survey Deep Learning on Graphs: A Survey
- GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
- ICLR 2017: Graph Attention Networks Graph Attention Networks ICLR 2017
- NeurIPS 2017: Inductive Representation Learning on Large Graphs Inductive Representation Learning on Large Graphs NeurIPS 2017
121-label node classification across protein-interaction graphs, predicting 121 non-exclusive Gene Ontology labels per protein from sequence/role features. Evaluated by F1.
Dataset details
Task
Protein-protein interaction node classification (121 GO labels, multi-label). The primary catalog metric is F1.
Data
Protein-protein interaction node classification (121 GO labels, multi-label).
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 F1 (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 | F1 ↑ | AUROC | Accuracy | F1-micro | Micro-F1 (L563) | Overlap Consistency | ROC-AUC | Topological Alignment | micro-averaged F1 (percent) | Paper |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | GAMLP(JK) | 0.9982
±
0.0001 | — | — | — | — | — | — | — | — | |
| 2 | GraphCON-GCN | 0.9960 | — | — | — | — | — | — | — | — | |
| 3 | GCNII | 0.9953
±
0.0001 | — | — | — | — | — | — | — | — | |
| 4 | GraphSAINT | 0.9950 | — | — | — | — | — | — | — | — | |
| 5 | GIST | 0.9950
±
0.0003 | — | — | — | — | — | — | — | — | |
| 6 | GCNII | 0.9950 | — | — | — | — | — | — | — | — | |
| 7 | GCNIII | 0.9950
±
0.0300 | — | — | — | — | — | — | — | — | |
| 8 | DenseMRGCN-14 | 0.9943 | — | — | — | — | — | — | — | — | |
| 9 | ResMRGCN-28 | 0.9941 | — | — | — | — | — | — | — | — | |
| 10 | Cluster-GCN | 0.9940 | — | — | — | — | — | — | — | — | |
| 11 | GraphCON-GAT | 0.9940 | — | — | — | — | — | — | — | — | |
| 12 | GAS (GCNII) | 0.9936
±
0.0002 | — | — | — | — | — | — | — | — | |
| 13 | Cluster-GCN | 0.9936 | — | — | — | — | — | — | — | — | |
| 14 | GraphSAINT | 0.9930
±
0.0010 | — | — | — | — | — | — | — | — | |
| 15 | Cluster-GCN | 0.9920
±
0.0004 | — | — | — | — | — | — | — | — | |
| 16 | PDE-GCN | 0.9920 | — | — | — | — | — | — | — | — | |
| 17 | AGNN-with share | 0.9910
±
0.0010 | — | — | — | — | — | — | — | — | |
| 18 | FreeKD-Prompt (GAT/GAT) | 0.9896 | — | — | — | — | — | — | — | — | |
| 19 | LMC (GCN) | 0.9887
±
0.0004 | — | — | — | — | — | — | — | — | |
| 20 | FreeKD | 0.9879 | — | — | — | — | — | — | — | — | |
| 21 | GaAN | 0.9871
±
0.0002 | — | — | — | — | — | — | — | — | |
| 22 | Full Prec. | 0.9870 | — | — | — | — | — | — | — | — | |
| 23 | VRGCN | 0.9860 | — | — | — | — | — | — | — | — | |
| 24 | SANE | 0.9856
±
0.0120 | — | — | — | — | — | — | — | — | |
| 25 | GeniePath | 0.9850 Accuracy
0.9850 | — | 0.9850 | — | — | — | — | — | — | |
| 26 | GCN | 0.9850 | — | — | — | — | — | — | — | — | |
| 27 | Attention-only | 0.9846
±
0.0009 | — | — | — | — | — | — | — | — | |
| 28 | G-CRD | 0.9842
±
0.0014 | — | — | — | — | — | — | — | — | |
| 29 | GIND | 0.9840 | — | — | — | — | — | — | — | — | |
| 30 | Max pooling | 0.9839
±
0.0005 | — | — | — | — | — | — | — | — | |
| 31 | Pairwise+sigmoid | 0.9839
±
0.0005 | — | — | — | — | — | — | — | — | |
| 32 | Pairwise+tanh | 0.9832
±
0.0018 | — | — | — | — | — | — | — | — | |
| 33 | GraphSAINT-EDGE | 0.9810
±
0.0070 | — | — | — | — | — | — | — | — | |
| 34 | GraphSAINT-RW | 0.9810
±
0.0040 | — | — | — | — | — | — | — | — | |
| 35 | GraphSAINT | 0.9810
±
0.0040 | — | — | — | — | — | — | — | — | |
| 36 | GraphSAINT-MRW | 0.9800
±
0.0060 | — | — | — | — | — | — | — | — | |
| 37 | EIGNN | 0.9800 | — | — | — | — | — | — | — | — | |
| 38 | SAGN+SLE | 0.9800
±
0.0010 | — | — | — | — | — | — | — | — | |
| 39 | GAT PTDNet | 0.9800
±
0.0220 | — | — | — | — | — | — | — | — | |
| 40 | Supervised Teacher | 0.9795
±
0.0010 | — | — | — | — | — | — | — | — | |
| 41 | KD | 0.9793
±
0.0026 | — | — | — | — | — | — | — | — | |
| 42 | Cluster-SAGE | 0.9790
±
0.0010 | — | — | — | — | — | — | — | — | |
| 43 | StochasticGCN | 0.9790
±
0.0000 | — | — | — | — | — | — | — | — | |
| 44 | Supervised Student | 0.9790
±
0.0045 | — | — | — | — | — | — | — | — | |
| 45 | SAGN | 0.9790
±
0.0010 | — | — | — | — | — | — | — | — | |
| 46 | GeniePath | 0.9790 | — | — | — | — | — | — | — | — | |
| 47 | LSP | 0.9781
±
0.0031 | — | — | — | — | — | — | — | — | |
| 48 | VR-GCN | 0.9780 Accuracy
0.9780 | — | 0.9780 | — | — | — | — | — | — | |
| 49 | GAT PTDNet-wl | 0.9780
±
0.0180 | — | — | — | — | — | — | — | — | |
| 50 | StoGCN | 0.9780 | — | — | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time