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 31, 2023

Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings
Sudhir Pratap Yadav, Rajendra Nagar, Suril V. Shah
Deep Reinforcement Learning Multi Task Learning Offline Reinforcement Learning Manipulation Task Vision Based Sequential Learning Offline Deep Reinforcement Learning

January 29, 2023

HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots
Bolin Zhang, Yunzhe Xu, Zhiying Tu, Dianhui Chu
Multi Task Learning Retrieval Augmented Generation Chatbot Response Generative Approach

January 27, 2023

Multi-task Highly Adaptive Lasso
Ivana Malenica, Rachael V. Phillips, Daniel Lazzareschi, Jeremy R. Coyle, Romain Pirracchio, Mark J. van der Laan
Multi Task Learning Multi Task Sparse Structure Adaptive Lasso

January 26, 2023

Transition-Aware Multi-Activity Knowledge Tracing
Siqian Zhao, Chunpai Wang, Shaghayegh Sahebi
Multi Task Learning Knowledge Transfer Knowledge Tracing

January 11, 2023

SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning
Chengzhi Wu, Linxi Qiu, Kanran Zhou, Julius Pfrommer, Jürgen Beyerer
Point Cloud Multi Task Learning Synthetic Image Computer Vision Task Benchmark Suite Segmentation Annotation Object Attribute

January 9, 2023

January 7, 2023

"It's a Match!" -- A Benchmark of Task Affinity Scores for Joint Learning
Raphael Azorin, Massimo Gallo, Alessandro Finamore, Dario Rossi, Pietro Michiardi
New Benchmark Multi Task Learning Joint Learning Task Affinity Affinity Score

January 6, 2023

Adaptive Pattern Extraction Multi-Task Learning for Multi-Step Conversion Estimations
Xuewen Tao, Mingming Ha, Xiaobo Guo, Qiongxu Ma, Hongwei Cheng, Wenfang Lin
Multi Task Learning Automated Conversion Task Vector Group Transformer

January 4, 2023

December 17, 2022

Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations
Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Yang Wang, Zhiheng Huang
Multi Task Learning Cross Task Generalization Compositional Task Table to Text Encode Task

December 16, 2022

FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks
Weilong Dong, Xinwei Wu, Junzhuo Li, Shuangzhi Wu, Chao Bian, Deyi Xiong
Multi Task Learning Shot Learning Centralized Learning Cross Task Generalization Shot Generalization One Shot Federated Learning Point Wise Weight

December 15, 2022

Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners
Zitian Chen, Yikang Shen, Mingyu Ding, Zhenfang Chen, Hengshuang Zhao, Erik Learned-Miller, Chuang Gan
Multi Task Learning Self Attention Mixture Component Expert Knowledge Vision Task Single Task Learning Cognitive Taskonomy

December 14, 2022

December 13, 2022

December 9, 2022

Multi-task Learning for Personal Health Mention Detection on Social Media
Olanrewaju Tahir Aduragba, Jialin Yu, Alexandra I. Cristea
Multi Task Learning Social Medium Target Emotion Emotion Detection Health Related Post