TU Dortmund
ENZYMES
Structure
600Graphs
33Nodes
62Edges
6Classes
3Node Feature Dim
Coverage
380Results
1Variants
58Papers
- Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
- MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks
- Position: Don't be Afraid of Over-Smoothing And Over-Squashing Position: Don't be Afraid of Over-Smoothing And Over-Squashing
- NeurIPS 2025: Enhancing Graph Classification Robustness with Singular Pooling Enhancing Graph Classification Robustness with Singular Pooling NeurIPS 2025
- Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization
- Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
- Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
- Exact Verification of Graph Neural Networks with Incremental Constraint Solving Exact Verification of Graph Neural Networks with Incremental Constraint Solving
- ICML 2025: Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification ICML 2025
- ICLR 2025: Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing ICLR 2025
- WWW 2025: DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach WWW 2025
- HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection
- Motif-driven Subgraph Structure Learning for Graph Classification Motif-driven Subgraph Structure Learning for Graph Classification
- NeurIPS 2024: ProG: A Graph Prompt Learning Benchmark ProG: A Graph Prompt Learning Benchmark NeurIPS 2024
- NeurIPS 2024: Variational Flow Matching for Graph Generation Variational Flow Matching for Graph Generation NeurIPS 2024
- NeurIPS 2024: Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models NeurIPS 2024
- Smoothed Graph Contrastive Learning via Seamless Proximity Integration Smoothed Graph Contrastive Learning via Seamless Proximity Integration
- ICML 2024: --Leman at the margin: When more expressivity matters --Leman at the margin: When more expressivity matters ICML 2024
- WWW 2024: Graph Contrastive Learning with Cohesive Subgraph Awareness Graph Contrastive Learning with Cohesive Subgraph Awareness WWW 2024
- AAAI 2023: Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns AAAI 2023
- ICLR 2023: Effective Structural Encodings via Local Curvature Profiles Effective Structural Encodings via Local Curvature Profiles ICLR 2023
- ICLR 2023: Equivariant Matrix Function Neural Networks Equivariant Matrix Function Neural Networks ICLR 2023
- ICLR 2023: Locality-Aware Graph Rewiring in GNNs Locality-Aware Graph Rewiring in GNNs ICLR 2023
- Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvature
- Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
- AAAI 2023: Union Subgraph Neural Networks Union Subgraph Neural Networks AAAI 2023
- ICML 2023: Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering ICML 2023
- NeurIPS 2023: The expressive power of pooling in Graph Neural Networks The expressive power of pooling in Graph Neural Networks NeurIPS 2023
- JMLR 2023: GNNBenchmark GNNBenchmark JMLR 2023
- ICML 2022: Revisiting Over-smoothing and Over-squashing using Ollivier's Ricci Curvature Revisiting Over-smoothing and Over-squashing using Ollivier's Ricci Curvature ICML 2022
- ICLR 2022: FoSR: First-order Spectral Rewiring for addressing Oversquashing in GNNs FoSR: First-order Spectral Rewiring for addressing Oversquashing in GNNs ICLR 2022
- Contrastive Graph Few-Shot Learning Contrastive Graph Few-Shot Learning
- NeurIPS 2022: Template based Graph Neural Network with Optimal Transport Distances Template based Graph Neural Network with Optimal Transport Distances NeurIPS 2022
- SoftEdge: Regularizing Graph Classification with Random Soft Edges SoftEdge: Regularizing Graph Classification with Random Soft Edges
- AAAI 2022: KerGNNs: Interpretable Graph Neural Networks with Graph Kernels KerGNNs: Interpretable Graph Neural Networks with Graph Kernels AAAI 2022
- ICML 2021: A New Perspective on the Effects of Spectrum in Graph Neural Networks A New Perspective on the Effects of Spectrum in Graph Neural Networks ICML 2021
- AAAI 2021: ifMixup: Interpolating Graph Pair to Regularize Graph Classification ifMixup: Interpolating Graph Pair to Regularize Graph Classification AAAI 2021
- ICML 2021: Breaking the Limits of Message Passing Graph Neural Networks Breaking the Limits of Message Passing Graph Neural Networks ICML 2021
- ICLR 2021: Topological Graph Neural Networks Topological Graph Neural Networks ICLR 2021
- AAAI 2020: Hierarchical Graph Capsule Network Hierarchical Graph Capsule Network AAAI 2020
- GraphCrop: Subgraph Cropping for Graph Classification GraphCrop: Subgraph Cropping for Graph Classification
- Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
- MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
- ICLR 2020: Wasserstein Embedding for Graph Learning Wasserstein Embedding for Graph Learning ICLR 2020
- ICLR 2020: On the Bottleneck of Graph Neural Networks and its Practical Implications On the Bottleneck of Graph Neural Networks and its Practical Implications ICLR 2020
- ICLR 2020: Memory-Based Graph Networks Memory-Based Graph Networks ICLR 2020
- WWW 2020: GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generation GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generation WWW 2020
- Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
- KDD 2019: DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification KDD 2019
- NeurIPS 2019: Wasserstein Weisfeiler-Lehman Graph Kernels Wasserstein Weisfeiler-Lehman Graph Kernels NeurIPS 2019
- KDD 2019: Graph Convolutional Networks with EigenPooling Graph Convolutional Networks with EigenPooling KDD 2019
- Graph Neural Networks With Convolutional ARMA Filters Graph Neural Networks With Convolutional ARMA Filters
- ICML 2018: Anonymous Walk Embeddings Anonymous Walk Embeddings ICML 2018
- 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
- NeurIPS 2016: The Multiscale Laplacian Graph Kernel The Multiscale Laplacian Graph Kernel NeurIPS 2016
- NeurIPS 2015: Diffusion-Convolutional Neural Networks Diffusion-Convolutional Neural Networks NeurIPS 2015
6-class graph classification TU Dortmund graph classification on 6 enzyme reaction classes (600 graphs, subset of BRENDA database). Uses the released node/edge labels or attributes; several social datasets are featureless. Evaluated by Accuracy.
Dataset details
Task
TU Dortmund graph classification on 6 enzyme reaction classes (600 graphs, subset of BRENDA database). The primary catalog metric is Accuracy.
Data
TU Dortmund graph classification on 6 enzyme reaction classes (600 graphs, subset of BRENDA database). The cataloged artifact reports 600 graphs, 6 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 ↑ | AUC | Clustering | Degree | F (macro) | F (micro) | Joint Node Label & Degree | NSPDK | Orbit | Uniqueness | Paper |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | GMN | 0.7866 | — | — | — | — | — | — | — | — | — | |
| 2 | MemGNN | 0.7550 | — | — | — | — | — | — | — | — | — | |
| 3 | TFGW SP | 0.7510
±
0.0500 | — | — | — | — | — | — | — | — | — | |
| 4 | TFGW ADJ | 0.7380
±
0.0460 | — | — | — | — | — | — | — | — | — | |
| 5 | PDF | 0.7350
±
0.0639 | — | — | — | — | — | — | — | — | — | |
| 6 | Norm-GN | 0.7333
±
0.0796 | — | — | — | — | — | — | — | — | — | |
| 7 | WWL | 0.7325
±
0.0087 | — | — | — | — | — | — | — | — | — | |
| 8 | A-NLSF | 0.7301
±
0.0080 | — | — | — | — | — | — | — | — | — | |
| 9 | MFN | 0.7290
±
0.0755 | — | — | — | — | — | — | — | — | — | |
| 10 | Spec-GN | 0.7250
±
0.0579 | — | — | — | — | — | — | — | — | — | |
| 11 | FGW - ADJ | 0.7220
±
0.0400 | — | — | — | — | — | — | — | — | — | |
| 12 | MEAN | 0.7167 | — | — | — | — | — | — | — | — | — | |
| 13 | UniAug | 0.7150
±
0.0585 | — | — | — | — | — | — | — | — | — | |
| 14 | WWL | 0.7140
±
0.0510 | — | — | — | — | — | — | — | — | — | |
| 15 | PGCN_g+DropNode | 0.7050 | — | — | — | — | — | — | — | — | — | |
| 16 | FGW - SP | 0.7050
±
0.0620 | — | — | — | — | — | — | — | — | — | |
| 17 | GFN | 0.7017
±
0.0558 | — | — | — | — | — | — | — | — | — | |
| 18 | GatedGCN | 0.7000
±
0.0494 | — | — | — | — | — | — | — | — | — | |
| 19 | WL | 0.6950
±
0.0320 | — | — | — | — | — | — | — | — | — | |
| 20 | GCN_g+DropNode | 0.6900 | — | — | — | — | — | — | — | — | — | |
| 21 | GAT | 0.6850
±
0.0524 | — | — | — | — | — | — | — | — | — | |
| 22 | RBF-WL | 0.6843
±
0.0147 | — | — | — | — | — | — | — | — | — | |
| 23 | FLAG | 0.6835
±
0.0745 | — | — | — | — | — | — | — | — | — | |
| 24 | SUM | 0.6833 | — | — | — | — | — | — | — | — | — | |
| 25 | MAX | 0.6833 | — | — | — | — | — | — | — | — | — | |
| 26 | UnionSNN | 0.6817
±
0.0570 | — | — | — | — | — | — | — | — | — | |
| 27 | GraphAug | 0.6814
±
0.0792 | — | — | — | — | — | — | — | — | — | |
| 28 | UnionGatedGCN | 0.6783
±
0.0687 | — | — | — | — | — | — | — | — | — | |
| 29 | UnionGIN | 0.6783
±
0.0610 | — | — | — | — | — | — | — | — | — | |
| 30 | GIN + FA | 0.6770
±
0.0530 | — | — | — | — | — | — | — | — | — | |
| 31 | GraphSNN | 0.6767
±
0.0374 | — | — | — | — | — | — | — | — | — | |
| 32 | GIN | 0.6767
±
0.0583 | — | — | — | — | — | — | — | — | — | |
| 33 | OT-GNN | 0.6730
±
0.0430 | — | — | — | — | — | — | — | — | — | |
| 34 | S-Mixup | 0.6685
±
0.0704 | — | — | — | — | — | — | — | — | — | |
| 35 | GCN | 0.6650
±
0.0691 | — | — | — | — | — | — | — | — | — | |
| 36 | GCN + 2FC | 0.6645 | — | — | — | — | — | — | — | — | — | |
| 37 | HGK-SP | 0.6636
±
0.0037 | — | — | — | — | — | — | — | — | — | |
| 38 | FCN (2FC) | 0.6617 | — | — | — | — | — | — | — | — | — | |
| 39 | PGCN_g+2FC | 0.6617 | — | — | — | — | — | — | — | — | — | |
| 40 | NLSF | 0.6594
±
0.0160 | — | — | — | — | — | — | — | — | — | |
| 41 | vanilla GCN | 0.6583
±
0.0461 | — | — | — | — | — | — | — | — | — | |
| 42 | GCN-4 | 0.6580
±
0.0460 | — | — | — | — | — | — | — | — | — | |
| 43 | DropGIN | 0.6580
±
0.0270 | — | — | — | — | — | — | — | — | — | |
| 44 | GATED-GCN-4 | 0.6570
±
0.0490 | — | — | — | — | — | — | — | — | — | |
| 45 | DiffPool +FA | 0.6570
±
0.0480 | — | — | — | — | — | — | — | — | — | |
| 46 | gh | 0.6565
±
0.0080 | — | — | — | — | — | — | — | — | — | |
| 47 | SGCL-T | 0.6530
±
0.0360 | — | — | — | — | — | — | — | — | — | |
| 48 | No Struct | 0.6520
±
0.0640 | — | — | — | — | — | — | — | — | — | |
| 49 | EigenPool | 0.6500 | — | — | — | — | — | — | — | — | — | |
| 50 | EigenPooling-1 | 0.6500 | — | — | — | — | — | — | — | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time