Classification on GE 75% corrupted features noise
57.9AccuracyLassoFlexNet
Evaluation Results
| Method | Links | |
|---|---|---|
| LassoFlexNetFeature Selection=End-to-end2026.03 | 57.9 | |
| LassoNet + MLPFeature Selection=LassoNet, Downstream Model=MLP2026.03 | 53.3 | |
| RF + MLPFeature Selection=RF, Downstream Model=MLP2026.03 | 53.3 | |
| XGBoost + MLPFeature Selection=XGBoost, Downstream Model=MLP2026.03 | 53 | |
| Deep Lasso + MLPFeature Selection=Deep Lasso, Downstream Model=MLP2026.03 | 51.7 | |
| No FS + MLPFeature Selection=None, Downstream Model=MLP2026.03 | 50.3 | |
| Univariate + MLPFeature Selection=Univariate, Downstream Model=MLP2026.03 | 49.5 | |
| 1L Lasso + MLPFeature Selection=1L Lasso, Downstream Model=MLP2026.03 | 49.5 | |
| Lasso + MLPFeature Selection=Lasso, Downstream Model=MLP2026.03 | 49 | |
| AGL + MLPFeature Selection=AGL, Downstream Model=MLP2026.03 | 49 |