Mantra Orientation
Description
Mantra Orientation
Dataset Overview
Lifting Methods
Structural-based Liftings
- Cellular: Cycle-based lifting
- Simplicial: Clique complex lifting
- Hypergraph: k-hop lifting
Feature Lifting
- Projected sum
Model Performance
| Model | Accuracy (%) | Std Dev (±) |
|---|---|---|
| GCN | 47.94 | 0.00 |
| GAT | 47.94 | 0.00 |
| GIN | 56.28 | 0.45 |
| SCN | 69.55 | 0.97 |
| SCCNN | 86.29 | 1.23 |
| SaNN | 61.65 | 0.55 |
| GCCN | 76.60 | 1.67 |
| HOPSE-M | 80.68 | 1.72 |
| HOPSE-G | 62.17 | 0.98 |
Key Insights
- SCCNN achieves the best performance with 86.29% accuracy
- HOPSE-M and GCCN also perform strongly, with 80.68% and 76.60% accuracy, respectively
- GCN and GAT show the lowest performance (47.94%)
- GIN, SCN, and SaNN achieve moderate results
Reproducibility
to be released