SOTAVerified

Multi-Task Learning

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

( Image credit: Cross-stitch Networks for Multi-task Learning )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2211–2220 of 3687 papers

TitleStatusHype
Thompson Sampling with a Mixture Prior—0
TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS—0
One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets—0
FedNILM: Applying Federated Learning to NILM Applications at the Edge—0
DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task LearningCode0
Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning—0
Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour—0
Beyond Black \& White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning—0
Emotion-Infused Models for Explainable Psychological Stress DetectionCode0
Transformer-based Multi-Task Learning for Adverse Effect Mention Analysis in Tweets—0
Show:102550
← PrevPage 222 of 369Next →
All datasetsQM9Cityscapes testNYUv2OMNIGLOTCelebAUTKFacewireframe dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PCGrad∆m%125.7—Unverified
2CAGrad∆m%112.8—Unverified
3IMTL-G∆m%77.2—Unverified
4Nash-MTL∆m%62—Unverified
5BayesAgg-MTL∆m%53.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SwinMTLmIoU76.41—Unverified
2Nash-MTLmIoU75.41—Unverified
3MultiObjectiveOptimizationmIoU66.63—Unverified
#ModelMetricClaimedVerifiedStatus
1SwinMTLMean IoU58.14—Unverified
2Nash-MTLMean IoU40.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Gumbel-Matrix RoutingAverage Accuracy93.52—Unverified
2Mixture-of-ExpertsAverage Accuracy92.19—Unverified
#ModelMetricClaimedVerifiedStatus
1MGDA-UBError8.25—Unverified
#ModelMetricClaimedVerifiedStatus
1BayesAgg-MTLdelta_m-2.23—Unverified
#ModelMetricClaimedVerifiedStatus
1LETRFH83.3—Unverified