Classification on Covertype
95.528AccuracyAgE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| AgE# Parameters=529,4292026.02 | 95.528 | — | — | — | |
| Large MLP# Parameters=1,048,5762026.02 | 95.353 | — | — | — | |
| TabGNS# Parameters=69,3132026.02 | 95.241 | — | — | — | |
| NMP-QATQuantization=Adaptive Neuron-level Mixed Precision2026.05 | 94.7 | — | — | — | |
| TabNAS# Parameters=142,1312026.02 | 94.691 | — | — | — | |
| QATBit-width=16-bit2026.05 | 94.13 | — | — | — | |
| FPBackbone=TabFormer2026.05 | 93.95 | — | — | — | |
| FPPrecision=Full Precision2026.05 | 93.95 | — | — | — | |
| QATBit-width=8-bit2026.05 | 93.3 | — | — | — | |
| OWQQuantization=Outlier-Aware2026.05 | 92.9 | — | — | — | |
| QATBit-width=4-bit2026.05 | 92.1 | — | — | — | |
| Q diag(s)Evaluation protocol=archived protocol2026.07 | 89.84 | — | — | — | |
| DenseEvaluation protocol=archived protocol2026.07 | 87.77 | — | — | — | |
| OWQBackbone=TabFormer2026.05 | 81.2 | — | — | — | |
| QATBit-width=1.58-bit2026.05 | 81.2 | — | — | — | |
| QATBit-width=16-bit2026.05 | 81 | — | — | — | |
| QATBit-width=8-bit2026.05 | 80.2 | — | — | — | |
| QATBit-width=4-bit2026.05 | 79.8 | — | — | — | |
| Clean Data2026.06 | 79.48 | — | — | — | |
| NMP-QATBackbone=TabFormer2026.05 | 79.3 | — | — | — | |
| DeMixrepair=true2026.06 | 78.62 | — | — | — | |
| DeMix-unifrepair=true2026.06 | 77.89 | — | — | — | |
| PPSOQuantization=Mixed Precision2026.05 | 77.3 | — | — | — | |
| DeMixrepair=false2026.06 | 77.05 | — | — | — | |
| DeMix-unifrepair=false2026.06 | 76.96 | — | — | — | |
| QATBit-width=1-bit2026.05 | 76.6 | — | — | — | |
| DDC2026.06 | 75.43 | — | — | — | |
| DDA-repair2026.06 | 75.03 | — | — | — | |
| QATBit-width=1.58-bit2026.05 | 74.8 | — | — | — | |
| MF-AdamEvaluation protocol=archived protocol2026.07 | 74.41 | — | — | — | |
| DDA-select2026.06 | 74.12 | — | — | — | |
| PPSOBackbone=TabFormer2026.05 | 73.3 | — | — | — | |
| QATBit-width=1-bit2026.05 | 72.3 | — | — | — | |
| Error. Data2026.06 | 71.91 | — | — | — | |
| ⋆-CL-CORAL2026.05 | 45.2 | — | — | — | |
| ⋆-CL-ANDMask2026.05 | 43.7 | — | — | — | |
| SARL2026.05 | 41.2 | — | — | — | |
| ⋆-CL-VREX2026.05 | 40.8 | — | — | — | |
| FDR2026.05 | 38.3 | — | — | — | |
| STAR2026.05 | 38.3 | — | — | — | |
| ER-ACE2026.05 | 37.7 | — | — | — | |
| ⋆-CL-MMD2026.05 | 37.6 | — | — | — | |
| LODE2026.05 | 37.5 | — | — | — | |
| AGEM2026.05 | 29 | — | — | — | |
| ⋆-CL-Fishr2026.05 | 27 | — | — | — | |
| EFC2026.05 | 25.8 | — | — | — | |
| SNR2026.05 | 25.4 | — | — | — | |
| SI2026.05 | 24.5 | — | — | — | |
| UPGD2026.05 | 23.4 | — | — | — | |
| COPE2026.05 | 9.4 | — | — | — | |
| Finetune2026.05 | 8.1 | — | — | — | |
| EWC2026.05 | 8 | — | — | — | |
| AUESamples per task=1502023.10 | — | 9 | — | — | |
| AUEn (samples per task)=102023.10 | — | 11 | 0 | 0.044 | |
| CatBoostaveraging=five train/test splits, tool=pytabkit2025.08 | — | 6.12 | — | — | |
| CondorSamples per task=1502023.10 | — | 7 | — | — | |
| Condorn (samples per task)=102023.10 | — | 9 | 0 | 0.184 | |
| DriftSurfSamples per task=1502023.10 | — | 9 | — | — | |
| DriftSurfn (samples per task)=102023.10 | — | 10 | 0 | 0.128 | |
| ELLASamples per task=1502023.10 | — | 10 | — | — | |
| ELLAn (samples per task)=102023.10 | — | 12 | 0.01 | 0.055 | |
| EWCSamples per task=1502023.10 | — | 8 | — | — | |
| EWCn (samples per task)=102023.10 | — | 9 | 0 | 0.313 | |
| GEMSamples per task=1502023.10 | — | 8 | — | — | |
| GEMn (samples per task)=102023.10 | — | 9 | 0.01 | 0.238 | |
| IMRCSamples per task=1502023.10 | — | 8 | — | — | |
| IMRCn (samples per task)=102023.10 | — | 8 | 0 | 0.275 | |
| LGBMaveraging=five train/test splits, tool=pytabkit2025.08 | — | 3.33 | — | — | |
| MERSamples per task=1502023.10 | — | 8 | — | — | |
| MERn (samples per task)=102023.10 | — | 8 | 0 | 0.25 | |
| MLP-PLRaveraging=five train/test splits, tool=pytabkit2025.08 | — | 3.64 | — | — | |
| MLP-RTDLaveraging=five train/test splits, tool=pytabkit2025.08 | — | 4.04 | — | — | |
| RealMLPaveraging=five train/test splits, tool=pytabkit2025.08 | — | 2.8 | — | — | |
| ResNet-RTDLaveraging=five train/test splits, tool=pytabkit2025.08 | — | 3.85 | — | — | |
| XGBaveraging=five train/test splits, tool=pytabkit2025.08 | — | 4.2 | — | — | |
| xRFMaveraging=five train/test splits, tool=pytabkit2025.08 | — | 2.57 | — | — |