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 676–700 of 3687 papers

Title	Date	Tasks	Status	Score
Is POS Tagging Necessary or Even Helpful for Neural Dependency Parsing?	Mar 6, 2020	Dependency ParsingFeature Engineering	CodeCode Available	5
It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers	Apr 25, 2022	Multi-Task LearningRelation	CodeCode Available	5
Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++	Jul 24, 2024	Multi-Task Learning	CodeCode Available	5
High-order Joint Constituency and Dependency Parsing	Sep 21, 2023	Dependency ParsingMulti-Task Learning	CodeCode Available	5
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning	Oct 16, 2023	Multi-Task LearningTransfer Learning	CodeCode Available	5
Intrinsically Motivated Open-Ended Multi-Task Learning Using Transfer Learning to Discover Task Hierarchy	Feb 19, 2021	Active LearningHierarchical Reinforcement Learning	CodeCode Available	5
Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation	Mar 30, 2021	Machine TranslationMulti-Task Learning	CodeCode Available	5
A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment	Aug 7, 2020	Action DetectionDecoder	CodeCode Available	5
Interpetable Target-Feature Aggregation for Multi-Task Learning based on Bias-Variance Analysis	Jun 12, 2024	ClusteringDimensionality Reduction	CodeCode Available	5
Instruction Tuned Models are Quick Learners	May 17, 2023	In-Context LearningMulti-Task Learning	CodeCode Available	5
Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings	Sep 14, 2022	FormMulti-Task Learning	CodeCode Available	5
A Unified Query-based Paradigm for Camouflaged Instance Segmentation	Aug 14, 2023	Boundary DetectionDecoder	CodeCode Available	5
A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing	Oct 1, 2022	Discourse ParsingMulti-Task Learning	CodeCode Available	5
Internal-transfer Weighting of Multi-task Learning for Lung Cancer Detection	Dec 16, 2019	Multi-Task Learning	CodeCode Available	5
A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis	Oct 6, 2020	Aspect Category Sentiment AnalysisDecoder	CodeCode Available	5
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity	Sep 5, 2019	Language ModelingLanguage Modelling	CodeCode Available	5
A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems	Apr 14, 2022	Multi-Task LearningRecommendation Systems	CodeCode Available	5
Multi-task Learning for Influence Estimation and Maximization	Apr 18, 2019	Multi-Task LearningRepresentation Learning	CodeCode Available	5
Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization	Sep 20, 2023	coreference-resolutionCoreference Resolution	CodeCode Available	5
A Unified Mammogram Analysis Method via Hybrid Deep Supervision	Aug 31, 2018	ClassificationGeneral Classification	CodeCode Available	5
Incorporating Joint Embeddings into Goal-Oriented Dialogues with Multi-Task Learning	Jan 28, 2020	DecoderGoal-Oriented Dialog	CodeCode Available	5
A Unified Framework for Multi-intent Spoken Language Understanding with prompting	Oct 7, 2022	Intent DetectionMulti-Task Learning	CodeCode Available	5
A Unified Framework for Generalizable Style Transfer: Style and Content Separation	Jun 13, 2018	DecoderMulti-Task Learning	CodeCode Available	5
Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning	Aug 1, 2021	DenoisingFew-Shot Learning	CodeCode Available	5
Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation	Mar 20, 2025	Multi-Task Learning	CodeCode Available	5

Show:10 25 50

← PrevPage 28 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