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

March 10, 2022

A Tree-Structured Multi-Task Model Recommender
Lijun Zhang, Xiao Liu, Hui Guan
Multi Task Learning Multi Task Vision Task

March 9, 2022

A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation
Xiuyuan Li, Jiangang Yu, Fengchao Li, Guowen An
Generative Adversarial Network Self Supervised Multi Task Learning Depth Estimation Monocular Video Monocular Visual Odometry

March 8, 2022

March 6, 2022

On Steering Multi-Annotations per Sample for Multi-Task Learning
Yuanze Li, Yiwen Guo, Qizhang Li, Hongzhi Zhang, Wangmeng Zuo
Multi Task Learning Instance Segmentation External Sample Task Allocation

March 1, 2022

February 28, 2022

One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification
Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Shan E Ahmed Raza, Fayyaz Minhas, David Snead, Nasir Rajpoot
Deep Learning Full Model Classification Code Multi Task Learning Image Segmentation Nucleus Classification Tissue Region

February 27, 2022

Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method
Yongjie Yang, Jinlei Zhang, Lixing Yang, Xiaohong Li, Ziyou Gao
Transformer Based Multi Task Learning Passenger Flow Prediction

February 26, 2022

Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression
Anu Jagannath, Jithin Jagannath
Multi Task Learning Model Compression Digital Modulation Signal Classification Edge Deployment Heterogeneous Wireless Spectral Angle Awareness

February 24, 2022

A Unified Framework for Campaign Performance Forecasting in Online Display Advertising
Jun Chen, Cheng Chen, Huayue Zhang, Qing Tan
Multi Task Learning Unified Framework Paper Bidding Bidding Strategy Display Advertising

February 22, 2022

February 20, 2022

Cross-Task Knowledge Distillation in Multi-Task Recommendation
Chenxiao Yang, Junwei Pan, Xiaofeng Gao, Tingyu Jiang, Dapeng Liu, Guihai Chen
Fine Grained Recommender System Multi Task Learning Multi Task Task Specific Knowledge Cross Task Knowledge Distillation

February 15, 2022

Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images
Hongzhi Zhu, Robert Rohling, Septimiu Salcudean
Multi Task Learning Visual Attention Chest X Ray Image Disease Classification Saliency Prediction Multi Task UNet

February 14, 2022

Trace norm regularization for multi-task learning with scarce data
Etienne Boursier, Mikhail Konobeev, Nicolas Flammarion
Multi Task Learning Multi Task Gradient Norm Scarce Data Data Scarce

February 11, 2022

Bench-Marking And Improving Arabic Automatic Image Captioning Through The Use Of Multi-Task Learning Paradigm
Muhy Eddin Za'ter, Bashar Talafha
Multi Task Learning Image Captioning Greater Public Use

February 10, 2022

Adaptive and Robust Multi-Task Learning
Yaqi Duan, Kaizheng Wang
Multi Task Learning Multi Task Adaptive Importance Adaptive Method Statistical Guarantee Outlier Detection Task

February 8, 2022

Generative multitask learning mitigates target-causing confounding
Taro Makino, Krzysztof J. Geras, Kyunghyun Cho
Multi Task Learning Multi Task Multitask Learning Faulty Negative Mitigation Causal Representation Multi Task Inference

Multi Task Learning

Papers

A Tree-Structured Multi-Task Model Recommender

A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation

HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks

YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers

On Steering Multi-Annotations per Sample for Multi-Task Learning

Multi-Task Multi-Scale Learning For Outcome Prediction in 3D PET Images

A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals

JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection

One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification

Short-term passenger flow prediction for multi-traffic modes: A Transformer and residual network based multi-task learning method

Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression

A Unified Framework for Campaign Performance Forecasting in Online Display Advertising

Structured Multi-task Learning for Molecular Property Prediction

ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challenges

Cross-Task Knowledge Distillation in Multi-Task Recommendation

Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images

Trace norm regularization for multi-task learning with scarce data

Bench-Marking And Improving Arabic Automatic Image Captioning Through The Use Of Multi-Task Learning Paradigm

Adaptive and Robust Multi-Task Learning

Generative multitask learning mitigates target-causing confounding