TU Dortmund
IMDB-BINARY
Structure
1,000Graphs
20Nodes
97Edges
2Classes
Coverage
189Results
1Variants
26Papers
- ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity
- Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
- NeurIPS 2025: Graph Persistence goes Spectral Graph Persistence goes Spectral NeurIPS 2025
- KDD 2025: Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature KDD 2025
- NeurIPS 2024: Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention NeurIPS 2024
- TMLR 2024: Graph Pooling via Ricci Flow Graph Pooling via Ricci Flow TMLR 2024
- Graph Learning with Distributional Edge Layouts Graph Learning with Distributional Edge Layouts
- Smoothed Graph Contrastive Learning via Seamless Proximity Integration Smoothed Graph Contrastive Learning via Seamless Proximity Integration
- Unifying Graph Contrastive Learning via Graph Message Augmentation Unifying Graph Contrastive Learning via Graph Message Augmentation
- NeurIPS 2023: Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks NeurIPS 2023
- ICLR 2023: Locality-Aware Graph Rewiring in GNNs Locality-Aware Graph Rewiring in GNNs ICLR 2023
- ICML 2023: Randomized Schur Complement Views for Graph Contrastive Learning Randomized Schur Complement Views for Graph Contrastive Learning ICML 2023
- NeurIPS 2023: Fine-grained Expressivity of Graph Neural Networks Fine-grained Expressivity of Graph Neural Networks NeurIPS 2023
- KDD 2023: Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization KDD 2023
- WWW 2023: Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification WWW 2023
- ICLR 2022: FoSR: First-order Spectral Rewiring for addressing Oversquashing in GNNs FoSR: First-order Spectral Rewiring for addressing Oversquashing in GNNs ICLR 2022
- Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification
- ICML 2022: Structural Entropy Guided Graph Hierarchical Pooling Structural Entropy Guided Graph Hierarchical Pooling ICML 2022
- ICLR 2022: Automated Data Augmentations for Graph Classification Automated Data Augmentations for Graph Classification ICLR 2022
- WWW 2021: Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices WWW 2021
- Pooling Architecture Search for Graph Classification Pooling Architecture Search for Graph Classification
- Recognizing Predictive Substructures with Subgraph Information Bottleneck Recognizing Predictive Substructures with Subgraph Information Bottleneck
- ICLR 2020: Graph Information Bottleneck for Subgraph Recognition Graph Information Bottleneck for Subgraph Recognition ICLR 2020
- ICML 2020: Contrastive Multi-View Representation Learning on Graphs Contrastive Multi-View Representation Learning on Graphs ICML 2020
- ICML 2020: Graph Homomorphism Convolution Graph Homomorphism Convolution ICML 2020
- ICML 2018: Graph Capsule Convolutional Neural Networks Graph Capsule Convolutional Neural Networks ICML 2018
2-class graph classification Binary graph classification of movie collaboration networks (action vs. romance). Uses the released node/edge labels or attributes; several social datasets are featureless. Evaluated by Accuracy.
Dataset details
Task
Binary graph classification of movie collaboration networks (action vs. romance). The primary catalog metric is Accuracy.
Data
Binary graph classification of movie collaboration networks (action vs. romance). The cataloged artifact reports 1,000 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 ↑ | F1 | ROC-AUC | Paper |
|---|---|---|---|---|---|
| 1 | ID-GNN+BEC | 0.8150
±
0.0240 | — | — | |
| 2 | GIN+BEC | 0.8080
±
0.0330 | — | — | |
| 3 | GCN+BEC | 0.7990
±
0.0340 | — | — | |
| 4 | GCN | 0.7980
±
0.0230 | — | — | |
| 5 | NC-GNN+BEC | 0.7960
±
0.0360 | — | — | |
| 6 | GraphSNN+BEC | 0.7940
±
0.0270 | — | — | |
| 7 | ID-GNN | 0.7930
±
0.0290 | — | — | |
| 8 | GAT +DEL-F | 0.7863
±
0.0054 | — | — | |
| 9 | GraphSNN | 0.7850
±
0.0230 | — | — | |
| 10 | EdgeDroppingDegree | 0.7850
±
0.0632 | — | — | |
| 11 | NC-GNN | 0.7840
±
0.0400 | — | — | |
| 12 | EdgeDropping | 0.7830
±
0.1083 | — | — | |
| 13 | Graph Transformer +DEL-F | 0.7828
±
0.0027 | — | — | |
| 14 | Graph Transformer + DEL-K | 0.7765
±
0.0049 | — | — | |
| 15 | GPS(DEL-F) | 0.7750
±
0.0065 | — | — | |
| 16 | GNTK | 0.7690
±
0.0360 | — | — | |
| 17 | GAT + DEL-K | 0.7686
±
0.0058 | — | — | |
| 18 | EdgeDroppingPR | 0.7680
±
0.0748 | — | — | |
| 19 | Graph Transformer + MPNN | 0.7651
±
0.0039 | — | — | |
| 20 | GraphAug | 0.7620
±
0.0040 | — | — | |
| 21 | Full B8C1 | 0.7620
±
0.0518 | — | — | |
| 22 | EdgeAddition | 0.7610
±
0.0563 | — | — | |
| 23 | GAT + Random distance | 0.7608
±
0.0048 | — | — | |
| 24 | GPS | 0.7600
±
0.0283 | — | — | |
| 25 | GAT + MPNN | 0.7585
±
0.0048 | — | — | |
| 26 | EdgeDroppingEVC | 0.7580
±
0.0626 | — | — | |
| 27 | SGCL-D | 0.7580
±
0.0190 | — | — | |
| 28 | GMCL-P | 0.7560
±
0.0317 | — | — | |
| 29 | CGRA | 0.7560
±
0.0050 | — | — | |
| 30 | GraphMAE | 0.7552
±
0.0066 | — | — | |
| 31 | MarkovDiffusion | 0.7530
±
0.0836 | — | — | |
| 32 | Graph Transformer + Random distance | 0.7527
±
0.0065 | — | — | |
| 33 | GMCL-D | 0.7520
±
0.0404 | — | — | |
| 34 | SGCL-T | 0.7520
±
0.0280 | — | — | |
| 35 | GIN-0 | 0.7510
±
0.0510 | — | — | |
| 36 | GMCL-M | 0.7510
±
0.0416 | — | — | |
| 37 | PAS | 0.7510
±
0.0532 | — | — | |
| 38 | Cluster-GT | 0.7510
±
0.0084 | — | — | |
| 39 | GIN | 0.7510
±
0.0510 | — | — | |
| 40 | SEP-G ICE | 0.7490
±
0.0085 | — | — | |
| 41 | SAGPool | 0.7487
±
0.0409 | — | — | |
| 42 | rLap | 0.7480
±
0.1017 | — | — | |
| 43 | G-Mixup | 0.7480
±
0.0040 | — | — | |
| 44 | FLAG | 0.7470
±
0.0080 | — | — | |
| 45 | AWL kernel | 0.7450
±
0.0590 | — | — | |
| 46 | Full B12C1 | 0.7450
±
0.0331 | — | — | |
| 47 | WL-W kernel | 0.7437
±
0.0083 | — | — | |
| 48 | GIN-ε | 0.7430
±
0.0510 | — | — | |
| 49 | ASAP | 0.7427
±
0.0397 | — | — | |
| 50 | MI | 0.7420
±
0.0070 | — | — |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time