TU Dortmund
D&D
Structure
1,178Graphs
284Nodes
716Edges
2Classes
82Node Feature Dim
Coverage
212Results
1Variants
37Papers
- USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation
- NeurIPS 2025: Enhancing Graph Classification Robustness with Singular Pooling Enhancing Graph Classification Robustness with Singular Pooling NeurIPS 2025
- ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity
- Fractal Graph Contrastive Learning Fractal Graph Contrastive Learning
- Efficient Mixed Precision Quantization in Graph Neural Networks Efficient Mixed Precision Quantization in Graph Neural Networks
- NeurIPS 2024: Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention NeurIPS 2024
- Dual-perspective Cross Contrastive Learning in Graph Transformers Dual-perspective Cross Contrastive Learning in Graph Transformers
- Graph Learning with Distributional Edge Layouts Graph Learning with Distributional Edge Layouts
- PAC Learnability under Explanation-Preserving Graph Perturbations PAC Learnability under Explanation-Preserving Graph Perturbations
- Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
- On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
- ICML 2022: Total Variation Graph Neural Networks Total Variation Graph Neural Networks ICML 2022
- NeurIPS 2022: Geodesic Graph Neural Network for Efficient Graph Representation Learning Geodesic Graph Neural Network for Efficient Graph Representation Learning NeurIPS 2022
- ICML 2022: Structural Entropy Guided Graph Hierarchical Pooling Structural Entropy Guided Graph Hierarchical Pooling ICML 2022
- Embedding Graphs on Grassmann Manifold Embedding Graphs on Grassmann Manifold
- AAAI 2021: Orthogonal Graph Neural Networks Orthogonal Graph Neural Networks AAAI 2021
- Pooling Architecture Search for Graph Classification Pooling Architecture Search for Graph Classification
- ICML 2021: How Framelets Enhance Graph Neural Networks How Framelets Enhance Graph Neural Networks ICML 2021
- WWW 2021: SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism WWW 2021
- AAAI 2020: Hierarchical Graph Capsule Network Hierarchical Graph Capsule Network AAAI 2020
- JMLR 2020: Decimated Framelet System on Graphs and Fast $ $-Framelet Transforms Decimated Framelet System on Graphs and Fast $ $-Framelet Transforms JMLR 2020
- Multi-grained Semantics-aware Graph Neural Networks Multi-grained Semantics-aware Graph Neural Networks
- GraphCrop: Subgraph Cropping for Graph Classification GraphCrop: Subgraph Cropping for Graph Classification
- AAAI 2020: Contrastive Self-supervised Learning for Graph Classification Contrastive Self-supervised Learning for Graph Classification AAAI 2020
- MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
- The Impact of Global Structural Information in Graph Neural Networks Applications The Impact of Global Structural Information in Graph Neural Networks Applications
- AAAI 2019: ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations AAAI 2019
- NeurIPS 2019: Wasserstein Weisfeiler-Lehman Graph Kernels Wasserstein Weisfeiler-Lehman Graph Kernels NeurIPS 2019
- Graph U-Nets Graph U-Nets
- KDD 2019: Graph Convolutional Networks with EigenPooling Graph Convolutional Networks with EigenPooling KDD 2019
- WWW 2019: Semi-Supervised Graph Classification: A Hierarchical Graph Perspective Semi-Supervised Graph Classification: A Hierarchical Graph Perspective WWW 2019
- Graph Neural Networks With Convolutional ARMA Filters Graph Neural Networks With Convolutional ARMA Filters
- Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
- ICML 2018: Graph Capsule Convolutional Neural Networks Graph Capsule Convolutional Neural Networks ICML 2018
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
- NeurIPS 2016: On Valid Optimal Assignment Kernels and Applications to Graph Classification On Valid Optimal Assignment Kernels and Applications to Graph Classification NeurIPS 2016
- ICML 2016: Learning Convolutional Neural Networks for Graphs Learning Convolutional Neural Networks for Graphs ICML 2016
2-class graph classification Graph classification of proteins into enzymes and non-enzymes via D&D representation. Uses the released node/edge labels or attributes; several social datasets are featureless. Evaluated by Accuracy.
Dataset details
Task
Graph classification of proteins into enzymes and non-enzymes via D&D representation. The primary catalog metric is Accuracy.
Data
Graph classification of proteins into enzymes and non-enzymes via D&D representation. The cataloged artifact reports 1,178 graphs, 2 target classes or tasks.
Features
The TU text format may contain discrete node or edge labels and optional continuous attributes. Social-network datasets commonly have no intrinsic node attributes, so papers often add constant or degree features; that choice changes the input.
Splits and evaluation
The catalog records these protocols or variants: 10-fold CV. Evaluation uses Accuracy (higher is better). Exact masks or folds must come from the cited release.
Quirks and pitfalls
TU datasets have no canonical train/test split. Report cross-validation folds, seeds, feature construction, and whether duplicate or isomorphic graphs were removed; published results can otherwise differ for protocol rather than model quality.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | Accuracy ↑ | Paper |
|---|---|---|---|
| 1 | GC-GNN (GCN) | 0.9210
±
0.0810 | |
| 2 | SUGAR | 0.8403
±
0.0133 | |
| 3 | Ortho-g-U-Nets | 0.8387 | |
| 4 | g-U-Nets | 0.8300 | |
| 5 | FGConv-Sum | 0.8290
±
0.0255 | |
| 6 | MathNet | 0.8250
±
0.0359 | |
| 7 | g-U-Nets | 0.8243 | Graph U-Nets
no code |
| 8 | structure2vec | 0.8222 | |
| 9 | CSSL-Reg A1-specific | 0.8218
±
0.0134 | |
| 10 | CSSL-Pretrain A1-specific | 0.8202
±
0.0142 | |
| 11 | AdamGNN | 0.8151
±
0.0156 | |
| 12 | GPS(DEL-F) [Final] | 0.8140
±
0.0046 | |
| 13 | GPS(RWSE, DEL-K) | 0.8121
±
0.0078 | |
| 14 | EGG | 0.8118
±
0.0114 | |
| 15 | HGP-SL | 0.8096
±
0.0126 | |
| 16 | SAGE | 0.8088
±
0.0233 | |
| 17 | CSSL-Pretrain A1-all | 0.8084
±
0.0124 | |
| 18 | CSSL-Pretrain A3-specific | 0.8084
±
0.0154 | |
| 19 | DiffPool | 0.8064 | Graph U-Nets
no code |
| 20 | CSSL-Reg A1-all | 0.8050
±
0.0134 | |
| 21 | GIN-AK+ | 0.8030
±
0.0310 | |
| 22 | CSSL-Pretrain A3-all | 0.8025
±
0.0141 | |
| 23 | FractalGCL | 0.8014
±
0.0012 | |
| 24 | StructPool | 0.8010
±
0.0177 | |
| 25 | DiffPool-NoLP | 0.7998 | Graph U-Nets
no code |
| 26 | WL | 0.7978 | |
| 27 | GL | 0.7970
±
0.0070 | |
| 28 | ESAN | 0.7970
±
0.0380 | |
| 29 | WWL | 0.7969
±
0.0050 | |
| 30 | CSSL-Reg A3-specific | 0.7966
±
0.0171 | |
| 31 | GraphSNN | 0.7960
±
0.0290 | |
| 32 | CSSL-Reg A3-all | 0.7958
±
0.0141 | |
| 33 | Graph Transformer +DEL-F | 0.7950
±
0.0015 | |
| 34 | TVGNN | 0.7950
±
0.0220 | |
| 35 | DC-GCL | 0.7943
±
0.0063 | |
| 36 | GraphMAE | 0.7942
±
0.0042 | |
| 37 | DGCNN | 0.7937 | |
| 38 | Graph Transformer + DEL-K | 0.7925
±
0.0011 | |
| 39 | WL-OA | 0.7920
±
0.0040 | |
| 40 | EdgePool | 0.7920
±
0.0261 | |
| 41 | Cluster-GT | 0.7915
±
0.0063 | |
| 42 | E-OA | 0.7900
±
0.0040 | |
| 43 | WL | 0.7900
±
0.0040 | |
| 44 | SP | 0.7900
±
0.0060 | |
| 45 | PAS | 0.7896
±
0.0368 | |
| 46 | GradGCL | 0.7895
±
0.0047 | |
| 47 | GAT +DEL-F | 0.7889
±
0.0034 | |
| 48 | MGCL | 0.7888
±
0.0038 | |
| 49 | RGCL | 0.7886
±
0.0048 | |
| 50 | V-OA | 0.7880
±
0.0030 |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time