Hypergraph Benchmarks
EAT
Structure
1Graphs
399Nodes
4Classes
Coverage
40Results
1Variants
5Papers
- Non-Dissipative Graph Propagation for Non-Local Community Detection Non-Dissipative Graph Propagation for Non-Local Community Detection
- Self-Contrastive Graph Diffusion Network Self-Contrastive Graph Diffusion Network
- AAAI 2022: Hard Sample Aware Network for Contrastive Deep Graph Clustering [5] Hard Sample Aware Network for Contrastive Deep Graph Clustering [5] AAAI 2022
- 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 European Airport Transactions hypergraph node classification (4 region classes, 399 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
European Airport Transactions hypergraph node classification (4 region classes, 399 nodes). The primary catalog metric is F1.
Data
European Airport Transactions hypergraph node classification (4 region classes, 399 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 ↑ | Conductance | NMI | Paper |
|---|---|---|---|---|---|
| 1 | SCAGC | 0.7277
±
0.0016 | — | — | |
| 2 | SCGC | 0.7222
±
0.0097 | — | — | |
| 3 | AGE | 0.7174
±
0.0093 | — | — | |
| 4 | DFCN | 0.7125
±
0.0031 | — | — | |
| 5 | DAEGC | 0.6987
±
0.0054 | — | — | |
| 6 | GAE | 0.6808
±
0.0176 | — | — | |
| 7 | ARGA | 0.6430
±
0.0195 | — | — | |
| 8 | SCGDN | 0.5763
±
0.0010 | — | — | |
| 9 | GraphLearner | 0.5753
±
0.0067 | — | — | |
| 10 | HSAN | 0.5726
±
0.0028 | — | — | |
| 11 | SSGC | 0.5279
±
0.0001 | — | — | |
| 12 | ARGA | 0.5275
±
0.0007 | — | — | |
| 13 | SDCN | 0.5066
±
0.0149 | — | — | |
| 14 | GCA | 0.4822
±
0.0033 | — | — | |
| 15 | GRACE | 0.4800
±
0.0300 Conductance
1.0000
±
0.0000 NMI
0.3100
±
0.0200 | 1.0000
±
0.0000 | 0.3100
±
0.0200 | |
| 16 | AE | 0.4787
±
0.0020 | — | — | |
| 17 | DCRN | 0.4706
±
0.0066 | — | — | |
| 18 | MVGRL | 0.4700
±
0.0600 Conductance
0.9300
±
0.1600 NMI
0.2200
±
0.0600 | 0.9300
±
0.1600 | 0.2200
±
0.0600 | |
| 19 | uAGNN | 0.4700
±
0.0500 Conductance
0.4000
±
0.3700 NMI
0.3200
±
0.0100 | 0.4000
±
0.3700 | 0.3200
±
0.0100 | |
| 20 | DEC | 0.4671
±
0.0012 | — | — | |
| 21 | DGI | 0.4600
±
0.0500 Conductance
0.7300
±
0.2200 NMI
0.2600
±
0.0200 | 0.7300
±
0.2200 | 0.2600
±
0.0200 | |
| 22 | AGE | 0.4554
±
0.0040 | — | — | |
| 23 | MGAE | 0.4308
±
0.0326 | — | — | |
| 24 | DFCN | 0.4295
±
0.0004 | — | — | |
| 25 | ProGCL | 0.4254
±
0.0045 | — | — | |
| 26 | SUBLIME | 0.4200
±
0.0600 Conductance
0.4900
±
0.1900 NMI
0.2200
±
0.0200 | 0.4900
±
0.1900 | 0.2200
±
0.0200 | |
| 27 | DAEGC | 0.4100
±
0.0200 Conductance
1.0000
±
0.0000 NMI
0.1300
±
0.0200 | 1.0000
±
0.0000 | 0.1300
±
0.0200 | |
| 28 | AGC-DRR | 0.3520
±
0.0017 | — | — | |
| 29 | DMoN | 0.3500
±
0.0400 Conductance
0.5900
±
0.4800 NMI
0.0700
±
0.0200 | 0.5900
±
0.4800 | 0.0700
±
0.0200 | |
| 30 | DEAGC | 0.3472
±
0.0016 | — | — | |
| 31 | DAEGC | 0.3472
±
0.0016 | — | — | |
| 32 | VGAER | 0.3400
±
0.0300 Conductance
0.5100
±
0.2000 NMI
0.1100
±
0.0600 | 0.5100
±
0.2000 | 0.1100
±
0.0600 | |
| 33 | SDCN | 0.3342
±
0.0310 | — | — | |
| 34 | MVGRL | 0.3288
±
0.0550 | — | — | |
| 35 | SUBLIME | 0.3231
±
0.0097 | — | — | |
| 36 | AFGRL | 0.3053
±
0.0147 | — | — | |
| 37 | GDCL | 0.2502
±
0.0021 | — | — | |
| 38 | K-means | 0.2396
±
0.0051 | — | — | |
| 39 | AutoSSL | 0.2182
±
0.0098 | — | — | |
| 40 | BGRL | 0.1900
±
0.0200 Conductance
0.9300
±
0.0100 NMI
0.0600
±
0.0200 | 0.9300
±
0.0100 | 0.0600
±
0.0200 |
SOTA performance
set a new SOTA at the time
matched the SOTA at the time