0.2% OS Yield Strength Prediction on Steel Property Prediction
2.603MAE (%)TabPFN
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| TabPFNFine-tuning Protocol=m.a.f.t. (multitask adapter fine-tuning)2026.03 | 2.603 | 87.66 | 58.78 | 96.99 | 9.73 | |
| TabPFNFine-tuning Protocol=m.f.t. (multitask fine-tuning)2026.03 | 2.604 | 87.75 | 58.66 | 96.98 | 9.64 | |
| TabPFNFine-tuning Protocol=s.f.t. (single-task fine-tuning)2026.03 | 2.614 | 87.54 | 58.23 | 96.97 | 9.29 | |
| TabPFNFine-tuning Protocol=n.f.t. (no fine-tuning)2026.03 | 2.654 | 87.03 | 57.69 | 96.93 | 8.04 | |
| XGBoostAlgorithm=Gradient Boosting2026.03 | 2.668 | 86.66 | 58.56 | 96.75 | 6.68 | |
| PLELearning Strategy=Progressive Layered Extraction2026.03 | 2.819 | 85.03 | 55.33 | 96.43 | 0.61 | |
| MMoELearning Strategy=Mixture-of-Experts2026.03 | 2.836 | 85.29 | 54.53 | 96.36 | 0.35 | |
| STEMLearning Strategy=Shared-Task Enhanced Model2026.03 | 2.848 | 84.89 | 54.07 | 96.21 | -0.4 | |
| MultiTabLearning Strategy=Multi-Tabular Learning2026.03 | 2.849 | 84.66 | 54.47 | 96.52 | 0.21 | |
| STLLearning Strategy=Single Task Learning2026.03 | 2.858 | 84.96 | 54.08 | 96.41 | 0 | |
| FT-TransformerArchitecture=Transformer-based2026.03 | 2.89 | 84.23 | 53.24 | 96.44 | -2.66 | |
| SAINTArchitecture=Transformer-based2026.03 | 2.915 | 84.08 | 53.43 | 96.23 | -0.77 | |
| MTLLearning Strategy=Multi-Task Learning2026.03 | 2.921 | 82.25 | 52.27 | 96.4 | -2.91 |