BayesAgg-MTL

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

Transfer LearningonUTKFace
delta_m· 2024-02-06
-2.23
SOTA
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning arXiv:2402.04005
Multi-Task LearningonUTKFace
delta_m· 2024-02-06
-2.23
SOTA
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning arXiv:2402.04005
Transfer LearningonQM9
∆m%· 2024-02-06
53.7
best: 125.7 (PCGrad)
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning arXiv:2402.04005
Multi-Task LearningonQM9
∆m%· 2024-02-06
53.7
best: 125.7 (PCGrad)
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning arXiv:2402.04005