Multi-Task Learning

16 benchmarks3687 papers

Multi-task learning aims to learn multiple different tasks simultaneously while maximizing performance on one or all of the tasks.

<span style="color:grey; opacity: 0.6">( Image credit: Cross-stitch Networks for Multi-task Learning )</span>

Benchmarks

Multi-Task Learning on MML

Average (%)

Multi-Task Learning on BBH-nlp

Average (%)

Multi-Task Learning on MGSM

Average (%)

Multi-Task Learning on BBH-alg

Average (%)

Multi-Task Learning on QM9

∆m%

Multi-Task Learning on Cityscapes test

mIoURMSE

Multi-Task Learning on NYUv2

Mean IoU

Multi-Task Learning on OMNIGLOT

Average Accuracy

Multi-Task Learning on CelebA

Error

Multi-Task Learning on MMLU (5-Shot)

MMLU (5-shot)

Multi-Task Learning on UTKFace

delta_m

Multi-Task Learning on wireframe dataset

FHsAP10sAP15

Multi-Task Learning on ChestX-ray14

delta_m