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

January 12, 2025

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
Hanwen Zhong, Jiaxin Chen, Yutong Zhang, Di Huang, Yunhong Wang
Vision Transformer Multi Task Learning Asynchronous Learning

January 11, 2025

CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening
Chong Zhong, Yang Li, Jinfeng Xu, Xiang Fu, Yunhao Liu, Qiuyi Huang, Danjuan Yang, Meiyan Li, Aiyi Liu, Alan H. Welsh, Xingtao Zhou, Bo Fu, Catherine C. Liu
Vision Transformer Multi Task Learning Fundus Image Multivariate Regression Covariate Representation High Myopia Ophthalmic Image

January 9, 2025

Supervised Learning with Evolving Tasks and Performance Guarantees
Verónica Álvarez, Santiago Mazuelas, Jose A. Lozano
Continual LEArning Multi Task Learning Supervised Learning Classification Task Multi Scenario Performance Guarantee Sequence Task

January 8, 2025

January 7, 2025

BASIC: Semi-supervised Multi-organ Segmentation with Balanced Subclass Regularization and Semantic-conflict Penalty
Zhenghao Feng, Lu Wen, Yuanyuan Xu, Binyu Yan, Xi Wu, Jiliu Zhou, Yan Wang
Multi Task Learning Class Imbalance Multi Organ Segmentation Appropriate Penalty Term Class Aware Regularization

January 2, 2025

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
Yongxian Wei, Anke Tang, Li Shen, Feng Xiong, Chun Yuan, Xiaochun Cao
Multi Task Learning Model Merging Merged Model

December 27, 2024

Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective
Yuanze Li, Chun-Mei Feng, Qilong Wang, Guanglei Yang, Wangmeng Zuo
Multi Task Learning Multi Task Back Propagation Related Task Auxiliary Task Unbiased Learning Strong Learner

December 26, 2024

Tint Your Models Task-wise for Improved Multi-task Model Merging
Aecheon Jung, Seunghwan Lee, Dongyoon Han, Sungeun Hong
Full Model Multi Task Learning Multi Task Model Task Specific Embeddings Color Filter

December 23, 2024

Collaborative Optimization in Financial Data Mining Through Deep Learning and ResNeXt
Pengbin Feng, Yankaiqi Li, Yijiashun Qi, Xiaojun Guo, Zhenghao Lin
LeArning Abstract Multi Task Learning Collaborative Optimization Multi Task Loss

December 18, 2024

Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning
Julien Audiffren, Christophe Broillet, Ljiljana Dolamic, Philippe Cudré-Mauroux
Practical Algorithm Multi Task Learning Taxonomy Construction Parallel Learning Incomplete Multi Label Learning Multi Label Document Classification

December 12, 2024

December 11, 2024

December 10, 2024

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning
Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang
LeArning Abstract Multi Task Learning Multi Task Domain Specific Hui Walter Paradigm Fast LoRA LLM Based Framework

December 9, 2024

Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models
Zhen Qi, Jiajing Chen, Shuo Wang, Bingying Liu, Hongye Zheng, Chihang Wang
Language Model Multi Task Learning GPT 4 Performance Improvement Multi Task Model

Multi Task Learning

Papers

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning

CeViT: Copula-Enhanced Vision Transformer in multi-task learning and bi-group image covariates with an application to myopia screening

Supervised Learning with Evolving Tasks and Performance Guarantees

Regularising NARX models with multi-task learning

TADFormer : Task-Adaptive Dynamic Transformer for Efficient Multi-Task Learning

BASIC: Semi-supervised Multi-organ Segmentation with Balanced Subclass Regularization and Semantic-conflict Penalty

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

Unprejudiced Training Auxiliary Tasks Makes Primary Better: A Multi-Task Learning Perspective

Tint Your Models Task-wise for Improved Multi-task Model Merging

Collaborative Optimization in Financial Data Mining Through Deep Learning and ResNeXt

Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning

No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods

Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps

Towards Better Multi-task Learning: A Framework for Optimizing Dataset Combinations in Large Language Models

Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning

MoSLD: An Extremely Parameter-Efficient Mixture-of-Shared LoRAs for Multi-Task Learning

Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AI

Preventing Conflicting Gradients in Neural Marked Temporal Point Processes

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning

Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models