Multi Task Learning

Multi-task learning (MTL) aims to improve model efficiency and generalization by training a single model to perform multiple related tasks simultaneously. Current research focuses on addressing challenges like task interference and optimization difficulties, exploring architectures such as Mixture-of-Experts (MoE), low-rank adaptors, and hierarchical models to enhance performance and efficiency across diverse tasks. MTL's significance lies in its potential to improve resource utilization and create more robust and adaptable AI systems, with applications spanning various fields including natural language processing, computer vision, and scientific modeling.

Papers

September 21, 2022

Extreme Multi-Domain, Multi-Task Learning With Unified Text-to-Text Transfer Transformers
Adebayo Oshingbesan, Courage Ekoh, Germann Atakpa, Yonah Byaruagaba
Multi Task Learning Domain Knowledge Unified Alignment Multi Domain Multi Domain Learning Text to Text Transfer Transformer Multi Task Transfer

September 20, 2022

Collaborative Anomaly Detection
Ke Bai, Aonan Zhang, Zhizhong Li, Ricardo Heano, Chong Wang, Lawrence Carin
Anomaly Detection Multi Task Learning Single Task Learning Task Embeddings Collaborative Anomaly Detection

September 14, 2022

Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings
Badr M. Abdullah, Bernd Möbius, Dietrich Klakow
Multi Task Learning Multiple Meaning First Integral Acoustic Word Embeddings Lexical Knowledge Lexical Representation Lexical Processing

September 13, 2022

MLT-LE: predicting drug-target binding affinity with multi-task residual neural networks
Elizaveta Vinogradova, Karina Pats, Ferdinand Molnár, Siamac Fazli
Multi Task Learning Multi Task Drug Discovery Estimated Team Strength Residual Neural Network Drug Target

September 9, 2022

Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction
Shunjie Chen, Xiaochuan Shi, Jingye Li, Shengqiong Wu, Hao Fei, Fei Li, Donghong Ji
Multi Task Learning Multi Task Label Space Emotion Embeddings Emotion Cause Pair Extraction Task Alignment Joint Alignment

September 6, 2022

Sequential Cross Attention Based Multi-task Learning
Sunkyung Kim, Hyesong Choi, Dongbo Min
Multi Task Learning Multi Scale Attention Module Self Attention Module Cross Task Attention Sequential Multi Task Learning

September 4, 2022

Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive Learning
Tianling Liu, Wennan Liu, Lequan Yu, Liang Wan, Tong Han, Lei Zhu
Multi Task Learning Joint predictioN Task Specific Feature Task Contrastive Learning

September 2, 2022

A Method for Discovering Novel Classes in Tabular Data
Colin Troisemaine, Joachim Flocon-Cholet, Stéphane Gosselin, Sandrine Vaton, Alexandre Reiffers-Masson, Vincent Lemaire
Multi Task Learning Practical Method Tabular Data Novel Class Discovery Classification Datasets Heterogeneous Tabular Data

September 1, 2022

Physics-informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites
Zeyu Cao, Wen Yao, Wei Peng, Xiaoya Zhang, Kairui Bao
Human Prediction Multi Task Learning Deformation Behavior Physic Informed Learning Multiple Satellite Human Stress Residual UNet Deformation Prediction

August 29, 2022

Prompt Tuning with Soft Context Sharing for Vision-Language Models
Kun Ding, Ying Wang, Pengzhang Liu, Qiang Yu, Haojian Zhang, Shiming Xiang, Chunhong Pan
Vision Language Model Multi Task Learning Shot Learning Prompt Tuning Pre Trained Vision Language Model Vision Language Prompt

August 24, 2022

Constraint-driven multi-task learning
Bogdan Cretu, Andrew Cropper
Multi Task Learning Logic Program Inductive Logic Programming Constraint Learning Iterative Neural Network

August 23, 2022

Retinal Structure Detection in OCTA Image via Voting-based Multi-task Learning
Jinkui Hao, Ting Shen, Xueli Zhu, Yonghuai Liu, Ardhendu Behera, Dan Zhang, Bang Chen, Jiang Liu, Jiong Zhang, Yitian Zhao
Multi Task Learning Optical Coherence Tomography Image Analysis Retinal Vessel Retinal Layer Retinal Feature

August 22, 2022

August 21, 2022

Multi-task Learning for Monocular Depth and Defocus Estimations with Real Images
Renzhi He, Hualin Hong, Boya Fu, Fei Liu
Multi Task Learning Depth Estimation Monocular Depth Estimation Monocular Depth Real Image Focal Length Defocus Map

August 19, 2022

August 17, 2022

Ask Question First for Enhancing Lifelong Language Learning
Han Wang, Ruiliu Fu, Xuejun Zhang, Jun Zhou, Qingwei Zhao
Language Model Multi Task Learning NLP Task Yes No Question Lifelong Learning Pseudo Labeled

August 11, 2022

MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization
Lei Qi, Hongpeng Yang, Yinghuan Shi, Xin Geng
Multi Task Learning Training Domain Multi Domain Learning Semi Supervised Domain Generalization

Multi Task Learning

Papers

Extreme Multi-Domain, Multi-Task Learning With Unified Text-to-Text Transfer Transformers

Collaborative Anomaly Detection

Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings

MLT-LE: predicting drug-target binding affinity with multi-task residual neural networks

Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction

Sequential Cross Attention Based Multi-task Learning

Joint Prediction of Meningioma Grade and Brain Invasion via Task-Aware Contrastive Learning

A Method for Discovering Novel Classes in Tabular Data

Physics-informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites

Prompt Tuning with Soft Context Sharing for Vision-Language Models

Constraint-driven multi-task learning

Retinal Structure Detection in OCTA Image via Voting-based Multi-task Learning

Detect Hate Speech in Unseen Domains using Multi-Task Learning: A Case Study of Political Public Figures

A Novel Multi-Task Learning Approach for Context-Sensitive Compound Type Identification in Sanskrit

Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding

Multi-task Learning for Monocular Depth and Defocus Estimations with Real Images

Curbing Task Interference using Representation Similarity-Guided Multi-Task Feature Sharing

Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding

Ask Question First for Enhancing Lifelong Language Learning

MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization