Wine quality
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Classification | Wine Quality (3 CV seeds) | F1 Score41.1 | 33 | |
| Imbalanced Classification | wine quality | F1-Score62.7 | 25 | |
| Counterfactual Explanation Generation | Wine Quality | R Score0.998 | 23 | |
| Regression | Wine Quality | RMSE0.2058 | 16 | |
| Regression | Wine Quality (test) | MSE0.439 | 15 | |
| Classification | Wine Quality | AW0.984 | 14 | |
| Prototype Fidelity Evaluation | Wine Quality (test) | Fidelity86.7 | 12 | |
| Conditional Anomaly Detection | Wine Quality (UCI ML) 2/3, 1/3 (train-test) | Mean Anomaly Agreement Score (AUC)75.1 | 10 | |
| Attribute selection in the counterfactual task | Wine Quality | NLL35.6 | 9 | |
| Classification | Wine Quality White UCIrvine | Macro F1 Score75.2 | 9 | |
| Classification | Wine Quality Red UCIrvine | Macro F170.7 | 9 | |
| Classification | Wine Quality (test) | Mean Loss52.84 | 8 | |
| Bandit Learning | Wine Quality Real Data Benign | Mean Regret666.74 | 8 | |
| Regression | Wine Quality Regime 2: High-Complexity | MSE0.8843 | 6 | |
| Synthetic Data Generation | Wine Quality | Average Runtime (seconds)0.0566 | 6 | |
| Classification | Wine Quality White tabular (test) | Accuracy53.5 | 5 | |
| Classification | Wine Quality Red (test) | Accuracy58.6 | 5 | |
| PU Classification | Wine Quality semi-synthetic | AUC0.78 | 5 | |
| Conditional Anomaly Detection | Wine Quality UCI 1/3 (test) | Mean Anomaly Agreement Score75.1 | 5 | |
| Classification | Wine Quality (10-fold CV) | P-Value0.001 | 5 | |
| Regression | Wine Quality UCI (test) | MI0.75 | 4 | |
| Tabular Regression | Wine Quality (UCI) | Total experiment time (s)3.4 | 4 | |
| Counterfactual Explanation Generation | wine-quality white | Validity1 | 4 | |
| Counterfactual Explanation Generation | wine-quality-red | Validity100 | 4 | |
| Outlier Explanation | wine-quality white | Average Run Time (s)0.13 | 4 |
Showing 25 of 32 rows