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 351–375 of 3687 papers

Title	Date	Tasks	Status	Hype
Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Task	Nov 1, 2021	Domain AdaptationMulti-Task Learning	CodeCode Available	1
Multi-Domain Multilingual Question Answering	Nov 1, 2021	Cross-Lingual TransferDomain Adaptation	CodeCode Available	1
MetaICL: Learning to Learn In Context	Oct 29, 2021	Few-Shot LearningIn-Context Learning	CodeCode Available	1
Conflict-Averse Gradient Descent for Multi-task Learning	Oct 26, 2021	Multi-Task Learning	CodeCode Available	1
Generalized Multi-Task Learning from Substantially Unlabeled Multi-Source Medical Image Data	Oct 25, 2021	Multi-Task LearningSegmentation	CodeCode Available	1
AutoMTL: A Programming Framework for Automating Efficient Multi-Task Learning	Oct 25, 2021	Multi-Task Learning	CodeCode Available	1
PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image	Oct 21, 2021	DecoderDepth Estimation	CodeCode Available	1
UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training	Oct 12, 2021	Data AugmentationMulti-Task Learning	CodeCode Available	1
Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation	Oct 8, 2021	Graph Neural NetworkMulti-Task Learning	CodeCode Available	1
Camera Calibration through Camera Projection Loss	Oct 7, 2021	3D ReconstructionAutonomous Driving	CodeCode Available	1
StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis	Oct 7, 2021	AttributeData Augmentation	CodeCode Available	1
SurvTRACE: Transformers for Survival Analysis with Competing Events	Oct 2, 2021	Multi-Task LearningSelection bias	CodeCode Available	1
SLAW: Scaled Loss Approximate Weighting for Efficient Multi-Task Learning	Sep 16, 2021	Drug DiscoveryMulti-Task Learning	CodeCode Available	1
DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients with Advanced Nasopharyngeal Carcinoma using Pretreatment PET/CT	Sep 16, 2021	Computed Tomography (CT)Multi-Task Learning	CodeCode Available	1
Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework	Sep 13, 2021	Community Question AnsweringMulti-Task Learning	CodeCode Available	1
ELIT: Emory Language and Information Toolkit	Sep 8, 2021	AMR ParsingConstituency Parsing	CodeCode Available	1
Multitask Balanced and Recalibrated Network for Medical Code Prediction	Sep 6, 2021	Medical Code PredictionMulti-Task Learning	CodeCode Available	1
Speech Emotion Recognition with Multi-Task Learning	Sep 6, 2021	Emotion ClassificationEmotion Recognition	CodeCode Available	1
Transformer Models for Text Coherence Assessment	Sep 5, 2021	Coherence EvaluationMachine Translation	CodeCode Available	1
A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting	Sep 2, 2021	AttributeMulti-Task Learning	CodeCode Available	1
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation	Sep 2, 2021	Clone DetectionCode Generation	CodeCode Available	1
MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification	Aug 29, 2021	ClassificationDisaster Response	CodeCode Available	1
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation	Aug 28, 2021	Data AugmentationDepth Estimation	CodeCode Available	1
YOLOP: You Only Look Once for Panoptic Driving Perception	Aug 25, 2021	Autonomous DrivingDrivable Area Detection	CodeCode Available	1
Federated Multi-Task Learning under a Mixture of Distributions	Aug 23, 2021	FairnessFederated Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 15 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