Hypergraph Benchmarks
BAT
Structure
1Graphs
131Nodes
4Classes
Coverage
53Results
1Variants
5Papers
- Non-Dissipative Graph Propagation for Non-Local Community Detection Non-Dissipative Graph Propagation for Non-Local Community Detection
- Reinforcement Graph Clustering with Unknown Cluster Number Reinforcement Graph Clustering with Unknown Cluster Number
- Self-Contrastive Graph Diffusion Network Self-Contrastive Graph Diffusion Network
- GraphLearner: Graph Node Clustering with Fully Learnable Augmentation GraphLearner: Graph Node Clustering with Fully Learnable Augmentation
- Simple Contrastive Graph Clustering Simple Contrastive Graph Clustering
4-class node classification Brazilian Airport Transactions hypergraph node classification (4 region classes, 131 nodes). Uses node-hyperedge incidence and the released node features. Clique expansion changes the input by discarding hyperedge identity. Evaluated by F1.
Dataset details
Task
Brazilian Airport Transactions hypergraph node classification (4 region classes, 131 nodes). The primary catalog metric is F1.
Data
Brazilian Airport Transactions hypergraph node classification (4 region classes, 131 nodes). The cataloged artifact reports 1 graphs, 4 target classes or tasks.
Features
The release represents higher-order membership with a node-hyperedge incidence relation and supplies node features where available. Some source datasets have no measured features and use documented synthetic features; clique expansion is an alternative representation that discards hyperedge identity.
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
Do not silently replace incidence propagation with clique expansion or merge distinct releases sharing a short name. Random synthetic features, split seeds, hyperedge multiplicity, and isolated-node handling can dominate results and must be reported.
Sources
SOTA Progression
new SOTA
matches SOTA at that time
other proposed result
other baseline result
Leaderboard
| # | Model | F1 ↑ | ARI | Conductance | NMI | Paper |
|---|---|---|---|---|---|---|
| 1 | GraphLearner | 0.7540
±
0.0088 | — | — | — | |
| 2 | SCGDN | 0.7449
±
0.0026 | — | — | — | |
| 3 | SCGC | 0.7222
±
0.0097 | — | — | — | |
| 4 | ARGA | 0.7174
±
0.0093 | — | — | — | |
| 5 | AGE | 0.7125
±
0.0031 | — | — | — | |
| 6 | SDCN | 0.7125
±
0.0031 | — | — | — | |
| 7 | MVGRL | 0.7047
±
0.0370 | — | — | — | |
| 8 | DAEGC | 0.6987
±
0.0054 | — | — | — | |
| 9 | GAE | 0.6808
±
0.0176 | — | — | — | |
| 10 | DCRN | 0.6740
±
0.0035 | — | — | — | |
| 11 | ProGCL | 0.5608
±
0.0089 | — | — | — | |
| 12 | uAGNN | 0.5400
±
0.1000 Conductance
0.7500
±
0.1700 NMI
0.4800
±
0.1200 | — | 0.7500
±
0.1700 | 0.4800
±
0.1200 | |
| 13 | GCA | 0.5371
±
0.0034 | — | — | — | |
| 14 | GRACE | 0.5300
±
0.0300 Conductance
0.8600
±
0.2400 NMI
0.3400
±
0.0600 | — | 0.8600
±
0.2400 | 0.3400
±
0.0600 | |
| 15 | DEAGC | 0.5223
±
0.0003 | — | — | — | |
| 16 | DAEGC | 0.5223
±
0.0003 | — | — | — | |
| 17 | BGRL | 0.5200
±
0.0300 Conductance
0.7200
±
0.1500 NMI
0.2300
±
0.0500 | — | 0.7200
±
0.1500 | 0.2300
±
0.0500 | |
| 18 | DFCN | 0.5090
±
0.0012 | — | — | — | |
| 19 | MGAE | 0.5083
±
0.0323 | — | — | — | |
| 20 | AE | 0.4787
±
0.0020 | — | — | — | |
| 21 | DEC | 0.4671
±
0.0012 | — | — | — | |
| 22 | AFGRL | 0.4653
±
0.0057 | — | — | — | |
| 23 | SDCN | 0.4645
±
0.0590 | — | — | — | |
| 24 | DGI | 0.4400
±
0.0600 Conductance
0.5800
±
0.1400 NMI
0.2900
±
0.0500 | — | 0.5800
±
0.1400 | 0.2900
±
0.0500 | |
| 25 | SUBLIME | 0.4400
±
0.0062 | — | — | — | |
| 26 | AGC-DRR | 0.4233
±
0.0051 | — | — | — | |
| 27 | GDCL | 0.3994
±
0.0057 | — | — | — | |
| 28 | DMoN | 0.3800
±
0.0700 Conductance
0.1900
±
0.3800 NMI
0.1500
±
0.0500 | — | 0.1900
±
0.3800 | 0.1500
±
0.0500 | |
| 29 | VGAER | 0.3600
±
0.0600 Conductance
0.5100
±
0.1500 NMI
0.1200
±
0.0600 | — | 0.5100
±
0.1500 | 0.1200
±
0.0600 | |
| 30 | AutoSSL | 0.3484
±
0.0015 | — | — | — | |
| 31 | MVGRL | 0.2964
±
0.0049 | — | — | — | |
| 32 | K-means | 0.2396
±
0.0051 | — | — | — | |
| 33 | DEC | — ARI
0.0799
±
0.0121 NMI
0.1410
±
0.0199 | 0.0799
±
0.0121 | — | 0.1410
±
0.0199 | |
| 34 | DCN | — ARI
0.1375
±
0.0605 NMI
0.1803
±
0.0773 | 0.1375
±
0.0605 | — | 0.1803
±
0.0773 | |
| 35 | IDEC | — ARI
0.0785
±
0.0131 NMI
0.1280
±
0.0174 | 0.0785
±
0.0131 | — | 0.1280
±
0.0174 | |
| 36 | AdaGAE | — ARI
0.0780
±
0.0041 NMI
0.1584
±
0.0078 | 0.0780
±
0.0041 | — | 0.1584
±
0.0078 | |
| 37 | MGAE | — ARI
0.2415
±
0.0170 NMI
0.3059
±
0.0206 | 0.2415
±
0.0170 | — | 0.3059
±
0.0206 | |
| 38 | DAEGC | — ARI
0.1818
±
0.0029 NMI
0.2143
±
0.0035 | 0.1818
±
0.0029 | — | 0.2143
±
0.0035 | |
| 39 | ARGA | — ARI
0.4202
±
0.0121 NMI
0.4909
±
0.0054 | 0.4202
±
0.0121 | — | 0.4909
±
0.0054 | |
| 40 | SDCN | — ARI
0.2104
±
0.0497 NMI
0.2574
±
0.0571 | 0.2104
±
0.0497 | — | 0.2574
±
0.0571 | |
| 41 | AGE | — ARI
0.2659
±
0.0183 NMI
0.3604
±
0.0154 | 0.2659
±
0.0183 | — | 0.3604
±
0.0154 | |
| 42 | MVGRL | — ARI
0.1345
±
0.0003 NMI
0.2933
±
0.0070 | 0.1345
±
0.0003 | — | 0.2933
±
0.0070 | |
| 43 | DFCN | — ARI
0.3776
±
0.0023 NMI
0.4877
±
0.0051 | 0.3776
±
0.0023 | — | 0.4877
±
0.0051 | |
| 44 | GDCL | — ARI
0.1933
±
0.0057 NMI
0.3170
±
0.0042 | 0.1933
±
0.0057 | — | 0.3170
±
0.0042 | |
| 45 | GCA | — ARI
0.2669
±
0.0285 NMI
0.3888
±
0.0023 | 0.2669
±
0.0285 | — | 0.3888
±
0.0023 | |
| 46 | MCGC | — ARI
0.0841
±
0.0032 NMI
0.2311
±
0.0056 | 0.0841
±
0.0032 | — | 0.2311
±
0.0056 | |
| 47 | AutoSSL | — ARI
0.1311
±
0.0081 NMI
0.1784
±
0.0098 | 0.1311
±
0.0081 | — | 0.1784
±
0.0098 | |
| 48 | AGC-DRR | — ARI
0.1459
±
0.0013 NMI
0.1991
±
0.0024 | 0.1459
±
0.0013 | — | 0.1991
±
0.0024 | |
| 49 | DCRN | — ARI
0.3976
±
0.0087 NMI
0.4723
±
0.0074 | 0.3976
±
0.0087 | — | 0.4723
±
0.0074 | |
| 50 | AFGRL | — ARI
0.2189
±
0.0074 NMI
0.2755
±
0.0062 | 0.2189
±
0.0074 | — | 0.2755
±
0.0062 |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time