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 3326–3350 of 3687 papers

Title	Date	Tasks	Status
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation	Jul 10, 2025	Multi-Task Learning	CodeCode Available
Sample-Level Weighting for Multi-Task Learning with Auxiliary Tasks	Jun 7, 2023	Multi-Task Learning	CodeCode Available
Graph Star Net for Generalized Multi-Task Learning	Jun 21, 2019	ClassificationGeneral Classification	CodeCode Available
Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5	Oct 31, 2022	Multi-Task LearningNatural Language Inference	CodeCode Available
An Attention-based Graph Neural Network for Heterogeneous Structural Learning	Dec 19, 2019	Graph EmbeddingGraph Neural Network	CodeCode Available
Graph Neural Networks for Surfactant Multi-Property Prediction	Jan 3, 2024	Ensemble LearningMulti-Task Learning	CodeCode Available
UU-Tax at SemEval-2022 Task 3: Improving the generalizability of language models for taxonomy classification through data augmentation	Oct 7, 2022	Binary ClassificationData Augmentation	CodeCode Available
Nowruz at SemEval-2022 Task 7: Tackling Cloze Tests with Transformers and Ordinal Regression	Apr 1, 2022	Multi-Task Learningregression	CodeCode Available
Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection	Jul 7, 2023	Multi-Task Learning	CodeCode Available
Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives	Aug 3, 2023	Multi-Task Learning	CodeCode Available
Auxiliary Quantile Forecasting with Linear Networks	Dec 5, 2022	Multi-Task LearningTime Series	CodeCode Available
Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering	May 31, 2022	ClusteringMulti-Task Learning	CodeCode Available
NUT-RC: Noisy User-generated Text-oriented Reading Comprehension	Dec 1, 2020	Answer SelectionArticles	CodeCode Available
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning	Nov 26, 2022	DisentanglementMeta-Learning	CodeCode Available
Simplified and Unified Analysis of Various Learning Problems by Reduction to Multiple-Instance Learning	Nov 14, 2019	Generalization BoundsMulti-Label Learning	CodeCode Available
Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders	Nov 14, 2023	Language ModellingMulti-Task Learning	CodeCode Available
A Physics Informed Neural Network (PINN) Methodology for Coupled Moving Boundary PDEs	Sep 17, 2024	Multi-Task Learning	CodeCode Available
Towards Viewpoint Invariant 3D Human Pose Estimation	Mar 23, 2016	3D Human Pose EstimationMulti-Task Learning	CodeCode Available
Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach	Jun 11, 2025	Community DetectionFairness	CodeCode Available
ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale	Oct 2, 2023	Multi-Task LearningTransfer Learning	CodeCode Available
DYNASHARE: DYNAMIC NEURAL NETWORKS FOR MULTI-TASK LEARNING	Sep 29, 2021	Dynamic neural networksMulti-Task Learning	CodeCode Available
Graph-based Knowledge Distillation by Multi-head Attention Network	Jul 4, 2019	Inductive BiasKnowledge Distillation	CodeCode Available
Adversarial Training for Code Retrieval with Question-Description Relevance Regularization	Oct 19, 2020	Multi-Task LearningRetrieval	CodeCode Available
Dynamic Multi-Task Learning for Face Recognition with Facial Expression	Nov 8, 2019	Face RecognitionFace Verification	CodeCode Available
MLT-LE: predicting drug-target binding affinity with multi-task residual neural networks	Sep 13, 2022	Drug DiscoveryMulti-Task Learning	CodeCode Available

Show:10 25 50

← PrevPage 134 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