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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 376–400 of 3687 papers

Title	Date	Tasks	Status	Hype
DeepCVA: Automated Commit-level Vulnerability Assessment with Deep Multi-task Learning	Aug 18, 2021	Multi-Task Learning	CodeCode Available	1
MobIE: A German Dataset for Named Entity Recognition, Entity Linking and Relation Extraction in the Mobility Domain	Aug 16, 2021	Entity LinkingMulti-Task Learning	CodeCode Available	1
An Effective System for Multi-format Information Extraction	Aug 16, 2021	DecoderDocument-level Event Extraction	CodeCode Available	1
Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning	Aug 11, 2021	DeblurringDepth Estimation	CodeCode Available	1
Mining the Benefits of Two-stage and One-stage HOI Detection	Aug 11, 2021	ClassificationHuman-Object Interaction Detection	CodeCode Available	1
Visible Watermark Removal via Self-calibrated Localization and Background Refinement	Aug 8, 2021	Multi-Task Learning	CodeCode Available	1
A Multi-Task Learning Framework for Multi-Target Stance Detection	Aug 1, 2021	Multi-Task LearningStance Detection	CodeCode Available	1
A Gradually Soft Multi-Task and Data-Augmented Approach to Medical Question Understanding	Aug 1, 2021	Data AugmentationDecoder	CodeCode Available	1
An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization	Aug 1, 2021	Knowledge GraphsMedical Named Entity Recognition	CodeCode Available	1
Towards robust vision by multi-task learning on monkey visual cortex	Jul 29, 2021	image-classificationImage Classification	CodeCode Available	1
ENHANCE (ENriching Health data by ANnotations of Crowd and Experts): A case study for skin lesion classification	Jul 27, 2021	DiagnosticLesion Classification	CodeCode Available	1
Hand Image Understanding via Deep Multi-Task Learning	Jul 24, 2021	3D Hand Pose EstimationHand Pose Estimation	CodeCode Available	1
Adaptive Transfer Learning on Graph Neural Networks	Jul 19, 2021	Meta-LearningMulti-Task Learning	CodeCode Available	1
TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer	Jul 18, 2021	Code GenerationMulti-Task Learning	CodeCode Available	1
Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals	Jul 18, 2021	Multi-Task LearningRetrieval	CodeCode Available	1
Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting	Jul 12, 2021	Multi-Task Learning	CodeCode Available	1
Heterogeneous Multi-task Learning with Expert Diversity	Jun 20, 2021	DiversityMixture-of-Experts	CodeCode Available	1
Polygonal Building Extraction by Frame Field Learning	Jun 19, 2021	Image SegmentationMulti-Task Learning	CodeCode Available	1
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation	Jun 16, 2021	Few-Shot Image Classificationimage-classification	CodeCode Available	1
Meta-Adaptive Nonlinear Control: Theory and Algorithms	Jun 11, 2021	Multi-Task LearningRepresentation Learning	CodeCode Available	1
Salient Object Ranking with Position-Preserved Attention	Jun 9, 2021	Image CroppingInstance Segmentation	CodeCode Available	1
VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation	Jun 8, 2021	Multi-Task LearningQuestion Answering	CodeCode Available	1
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks	Jun 8, 2021	Domain GeneralizationLanguage Modeling	CodeCode Available	1
Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation	Jun 7, 2021	Graph Neural NetworkMulti-Task Learning	CodeCode Available	1
Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning	Jun 6, 2021	DiversityMulti Label Text Classification	CodeCode Available	1

Show:10 25 50

← PrevPage 16 of 148Next →

All datasets QM9 Cityscapes test NYUv2 OMNIGLOT CelebA UTKFace wireframe dataset

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	PCGrad	∆m%	125.7	—	Unverified
2	CAGrad	∆m%	112.8	—	Unverified
3	IMTL-G	∆m%	77.2	—	Unverified
4	Nash-MTL	∆m%	62	—	Unverified
5	BayesAgg-MTL	∆m%	53.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SwinMTL	mIoU	76.41	—	Unverified
2	Nash-MTL	mIoU	75.41	—	Unverified
3	MultiObjectiveOptimization	mIoU	66.63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SwinMTL	Mean IoU	58.14	—	Unverified
2	Nash-MTL	Mean IoU	40.13	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Gumbel-Matrix Routing	Average Accuracy	93.52	—	Unverified
2	Mixture-of-Experts	Average Accuracy	92.19	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	MGDA-UB	Error	8.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BayesAgg-MTL	delta_m	-2.23	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LETR	FH	83.3	—	Unverified