Regression on Synthetic two-feature data Linear, n=1000
0.9957Mean R^2LightGBM, rel-s features
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LightGBM, rel-s featuresSample size (n)=10002025.12 | 0.9957 | 0.0006 | |
| NW + relationsNorm/Embedding Type=L2 norm, Sample size (n)=10002025.12 | 0.9935 | 0.0011 | |
| NW + relationsNorm/Embedding Type=MLP embeddings, Sample size (n)=10002025.12 | 0.9901 | 0.0012 | |
| NW + relationsNorm/Embedding Type=learnable norm, Sample size (n)=10002025.12 | 0.986 | 0.0014 | |
| TabRelSample size (n)=10002025.12 | 0.9486 | 0.1042 | |
| NW, no rel-s infoNorm/Embedding Type=learnable norm, Sample size (n)=10002025.12 | 0.9025 | 0.0063 | |
| NW, no rel-s infoNorm/Embedding Type=L2 norm, Sample size (n)=10002025.12 | 0.9024 | 0.0064 | |
| LightGBM, no rel-s infoSample size (n)=10002025.12 | 0.8871 | 0.0099 | |
| NW, rel-s featuresSample size (n)=10002025.12 | -0.16 | 0.0421 |