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

April 29, 2023

An Extensible Multimodal Multi-task Object Dataset with Materials
Trevor Standley, Ruohan Gao, Dawn Chen, Jiajun Wu, Silvio Savarese
Multi Task Learning Multimodal Dataset Material Response Product Taxonomy

April 27, 2023

$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
Chengyue Wu, Teng Wang, Yixiao Ge, Zeyu Lu, Ruisong Zhou, Ying Shan, Ping Luo
Transfer Learning Multi Task Learning Multimodal Foundation Model Parameter Efficient Transfer Learning Cross Modality Transfer P Tuning

April 21, 2023

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge
Alexander Wong, Yifan Wu, Saad Abbasi, Saeejith Nair, Yuhao Chen, Mohammad Javad Shafiee
Multi Task Learning Self Attention Multi Task Robotic Grasping Computer Vision Task Deep Learning Based Computer Vision

April 18, 2023

AutoTaskFormer: Searching Vision Transformers for Multi-task Learning
Yang Liu, Shen Yan, Yuge Zhang, Kan Ren, Quanlu Zhang, Zebin Ren, Deng Cai, Mi Zhang
Vision Transformer Multi Task Learning Multi Task Vision Transformer

April 17, 2023

AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning
Marina Neseem, Ahmed Agiza, Sherief Reda
Multi Task Learning Single Task Task Specific Decoder Task Inference Adaptive Inference

April 7, 2023

Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing
Ziming Huang, Zhuoxuan Jiang, Ke Wang, Juntao Li, Shanshan Feng, Xian-Ling Mao
Multi Task Learning Dialog Model

April 3, 2023

Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation
Hanrong Ye, Dan Xu
Multi Task Learning Segmentation Based Approach Depth Estimation 3D Object 3D Detection Multi Task Benchmark 3D City Task Representation

March 31, 2023

March 30, 2023

March 28, 2023

Predicting Adverse Neonatal Outcomes for Preterm Neonates with Multi-Task Learning
Jingyang Lin, Junyu Chen, Hanjia Lyu, Igor Khodak, Divya Chhabra, Colby L Day Richardson, Irina Prelipcean, Andrew M Dylag, Jiebo Luo
Multi Task Learning Neonatal Outcome

March 26, 2023

Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma
Xiaofei Wang, Stephen Price, Chao Li
Multi Task Learning Digital Pathology Histopathological Image Multi Omics Diffuse Glioma Marker Code

March 25, 2023

Identification of Negative Transfers in Multitask Learning Using Surrogate Models
Dongyue Li, Huy L. Nguyen, Hongyang R. Zhang
Multi Task Learning Surrogate Model Person Identification Multitask Learning Task Similarity Negative Transfer

March 21, 2023

BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements
Girish Narayanswamy, Yujia Liu, Yuzhe Yang, Chengqian Ma, Xin Liu, Daniel McDuff, Shwetak Patel
Computer Vision Multi Task Learning Physiological Signal Salient Object Human Visual Perception Spatial Distancing

March 16, 2023

Efficient Computation Sharing for Multi-Task Visual Scene Understanding
Sara Shoouri, Mingyu Yang, Zichen Fan, Hun-Seok Kim
Multi Task Learning Multi Task Visual Task Redundancy Aware Domain Task

March 14, 2023

Relational Multi-Task Learning: Modeling Relations between Data and Tasks
Kaidi Cao, Jiaxuan You, Jure Leskovec
Raw Data Multi Task Learning New Task Multi Task Model Relation Modeling

Multi Task Learning

Papers

An Extensible Multimodal Multi-task Object Dataset with Materials

$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation

Rubik's Optical Neural Networks: Multi-task Learning with Physics-aware Rotation Architecture

A Multi-Task Approach to Robust Deep Reinforcement Learning for Resource Allocation

Curriculum Modeling the Dependence among Targets with Multi-task Learning for Financial Marketing

Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge

AutoTaskFormer: Searching Vision Transformers for Multi-task Learning

AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning

Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing

Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation

Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation

Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness

A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision

Multi-Task Learning for Post-transplant Cause of Death Analysis: A Case Study on Liver Transplant

Predicting Adverse Neonatal Outcomes for Preterm Neonates with Multi-Task Learning

Multi-task Learning of Histology and Molecular Markers for Classifying Diffuse Glioma

Identification of Negative Transfers in Multitask Learning Using Surrogate Models

BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements

Efficient Computation Sharing for Multi-Task Visual Scene Understanding

Relational Multi-Task Learning: Modeling Relations between Data and Tasks