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

August 10, 2023

Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation
Xinyu Lyu, Jingwei Liu, Yuyu Guo, Lianli Gao
Multi Task Learning Scene Graph Scene Graph Generation

August 5, 2023

Data Fusion for Multi-Task Learning of Building Extraction and Height Estimation
Saad Ahmed Jamal, Arioluwa Aribisala
Multi Task Learning Multitask Learning Information Fusion Height Estimation Building Extraction Synthetic Weather Radar

August 3, 2023

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives
Chuntao Ding, Zhichao Lu, Shangguang Wang, Ran Cheng, Vishnu Naresh Boddeti
Multi Task Learning Task Agnostic Feature Task Interference

August 2, 2023

Multi-task learning for classification, segmentation, reconstruction, and detection on chest CT scans
Weronika Hryniewska-Guzik, Maria Kędzierska, Przemysław Biecek
Classification Code Data Detection Loss Function Multi Task Learning Multi Task Segmentation Task Multi Task Learning Framework Chest Computed Tomography

July 31, 2023

FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration
Zhijian Huang, Sihao Lin, Guiyu Liu, Mukun Luo, Chaoqiang Ye, Hang Xu, Xiaojun Chang, Xiaodan Liang
Autonomous Driving Multi Task Learning Multi Task Multi Modality Fusion Calibrated Learning Multi Task 3D

July 28, 2023

July 25, 2023

When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review
Maxime Fontana, Michael Spratling, Miaojing Shi
Multi Task Learning Fully Supervised Learning Paradigm Partial Supervision Task Relationship Task Grouping

July 24, 2023

DEPHN: Different Expression Parallel Heterogeneous Network using virtual gradient optimization for Multi-task Learning
Menglin Kong, Ri Su, Shaojie Zhao, Muzhou Hou
Multi Task Learning Gradient Based Optimization Task Correlation Shared Model

July 20, 2023

Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection
Yinghui Xing, Dexuan Kong, Shizhou Zhang, Geng Chen, Lingyan Ran, Peng Wang, Yanning Zhang
Multi Task Learning Pre Training Large Pre Trained Model Camouflaged Object Detection Task Specific Adapter Multi Task Adaptation Camouflage Object Detection

July 19, 2023

Forecasting Early with Meta Learning
Shayan Jawed, Kiran Madhusudhanan, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme
Time Series Multi Task Learning Meta Learning Adversarial Learning State of the Art Forecasting

July 17, 2023

A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images
Yan-Jie Zhou, Wei Liu, Yuan Gao, Jing Xu, Le Lu, Yuping Duan, Hao Cheng, Na Jin, Xiaoyong Man, Shuang Zhao, Yu Wang
Multi Task Learning Medical Image Skin Lesion Large Scale Medical Differential Diagnosis Computer Aided

July 10, 2023

July 7, 2023

July 4, 2023

Multi-Task Learning to Enhance Generalizability of Neural Network Equalizers in Coherent Optical Systems
Sasipim Srivallapanondh, Pedro J. Freire, Ashraful Alam, Nelson Costa, Bernhard Spinnler, Antonio Napoli, Egor Sedov, Sergei K. Turitsyn, Jaroslaw E. Prilepsky
Multi Task Learning Multi Task Stronger Generalizability Parametric Equalizer Q Value Neural Network Based Equalizer Coherent Optical

July 3, 2023

Multi-Task Learning Improves Performance In Deep Argument Mining Models
Amirhossein Farzam, Shashank Shekhar, Isaac Mehlhaff, Marco Morucci
Multi Task Learning Large Corpus System Performance Abstract Argumentation Argument Mining Task

Multi Task Learning

Papers

Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation

Data Fusion for Multi-Task Learning of Building Extraction and Height Estimation

Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives

Multi-task learning for classification, segmentation, reconstruction, and detection on chest CT scans

FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration

Improvable Gap Balancing for Multi-Task Learning

TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts

When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review

DEPHN: Different Expression Parallel Heterogeneous Network using virtual gradient optimization for Multi-task Learning

Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection

Forecasting Early with Meta Learning

A Novel Multi-Task Model Imitating Dermatologists for Accurate Differential Diagnosis of Skin Diseases in Clinical Images

Advances and Challenges in Meta-Learning: A Technical Review

Gradient Surgery for One-shot Unlearning on Generative Model

Derivative Free Weight-space Ensembling

TBGC: Task-level Backbone-Oriented Gradient Clip for Multi-Task Foundation Model Learning

Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection

STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map

Multi-Task Learning to Enhance Generalizability of Neural Network Equalizers in Coherent Optical Systems

Multi-Task Learning Improves Performance In Deep Argument Mining Models