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 276–300 of 3687 papers

Title	Date	Tasks	Status	Hype
DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect Estimation	Jul 19, 2022	Causal InferenceMulti-Task Learning	CodeCode Available	1
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes	Jul 16, 2022	Autonomous DrivingDepth Estimation	CodeCode Available	1
Learning to Estimate External Forces of Human Motion in Video	Jul 12, 2022	3D Human Pose EstimationMulti-Task Learning	CodeCode Available	1
A Large Scale Search Dataset for Unbiased Learning to Rank	Jul 7, 2022	Causal DiscoveryLanguage Modelling	CodeCode Available	1
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning	Jul 4, 2022	AttributeContrastive Learning	CodeCode Available	1
Saliency-Regularized Deep Multi-Task Learning	Jul 3, 2022	image-classificationImage Classification	CodeCode Available	1
DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning	Jun 17, 2022	2D Semantic SegmentationDepth Estimation	CodeCode Available	1
On Privacy and Personalization in Cross-Silo Federated Learning	Jun 16, 2022	Federated LearningMulti-Task Learning	CodeCode Available	1
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning	Jun 15, 2022	AttributeEmotion Classification	CodeCode Available	1
A Multi-task Framework for Infrared Small Target Detection and Segmentation	Jun 14, 2022	Multi-Task Learningobject-detection	CodeCode Available	1
Human Mobility Prediction with Causal and Spatial-constrained Multi-task Network	Jun 12, 2022	Multi-Task Learning	CodeCode Available	1
Learning Ego 3D Representation as Ray Tracing	Jun 8, 2022	3D Object DetectionBEV Segmentation	CodeCode Available	1
RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction	Jun 7, 2022	Document-level Event ExtractionEvent Extraction	CodeCode Available	1
PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding	Jun 5, 2022	Feature EngineeringMulti-Task Learning	CodeCode Available	1
Stochastic Multiple Target Sampling Gradient Descent	Jun 4, 2022	Multi-Task Learning	CodeCode Available	1
FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation	May 31, 2022	Deep LearningMulti-Task Learning	CodeCode Available	1
Multi-Task Learning with Multi-Query Transformer for Dense Prediction	May 28, 2022	DecoderMulti-Task Learning	CodeCode Available	1
Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges	May 28, 2022	Continual LearningContinuous Control	CodeCode Available	1
Cascading Residual Graph Convolutional Network for Multi-Behavior Recommendation	May 26, 2022	Multi-Task Learning	CodeCode Available	1
ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts	May 24, 2022	Few-Shot LearningLanguage Modelling	CodeCode Available	1
uGLAD: Sparse graph recovery by optimizing deep unrolled networks	May 23, 2022	Multi-Task Learning	CodeCode Available	1
On Measuring Social Biases in Prompt-Based Multi-Task Learning	May 23, 2022	FormLanguage Modeling	CodeCode Available	1
Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT	May 19, 2022	Multi-Task Learningnamed-entity-recognition	CodeCode Available	1
Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment	May 6, 2022	Automatic Speech RecognitionAutomatic Speech Recognition (ASR)	CodeCode Available	1
UniTE: Unified Translation Evaluation	Apr 28, 2022	Machine TranslationMulti-Task Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 12 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