paper-with-me

홈 › Papers

Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras

2024-04-29 · Jun Yu, Yutong Dai, Xiaokang Liu, Jin Huang, Yishan Shen, Ke Zhang, Rong Zhou, Eashan Adhikarla, Wenxuan Ye, Yixin Liu, Zhaoming Kong, Kai Zhang, Yilong Yin, Vinod Namboodiri, Brian D. Davison, Jason H. Moore, Yong Chen

MTL is a learning paradigm that effectively leverages both task-specific and shared information to address multiple related tasks simultaneously. In contrast to STL, MTL offers a suite of benefits that enhance both the training process and the inference efficiency. MTL's key advantages encompass streamlined model architecture, performance enhancement, and cross-domain generalizability. Over the past twenty years, MTL has become widely recognized as a flexible and effective approach in various fields, including CV, NLP, recommendation systems, disease prognosis and diagnosis, and robotics. This survey provides a comprehensive overview of the evolution of MTL, encompassing the technical aspects of cutting-edge methods from traditional approaches to deep learning and the latest trend of pretrained foundation models. Our survey methodically categorizes MTL techniques into five key areas: regularization, relationship learning, feature propagation, optimization, and pre-training. This categorization not only chronologically outlines the development of MTL but also dives into various specialized strategies within each category. Furthermore, the survey reveals how the MTL evolves from handling a fixed set of tasks to embracing a more flexible approach free from task or modality constraints. It explores the concepts of task-promptable and -agnostic training, along with the capacity for ZSL, which unleashes the untapped potential of this historically coveted learning paradigm. Overall, we hope this survey provides the research community with a comprehensive overview of the advancements in MTL from its inception in 1997 to the present in 2023. We address present challenges and look ahead to future possibilities, shedding light on the opportunities and potential avenues for MTL research in a broad manner. This project is publicly available at https://github.com/junfish/Awesome-Multitask-Learning.

📄 PDF Abstract BibTeX arXiv:2404.18961

Code (2)

junfish/Awesome-Multitask-Learning 공식 구현 pytorch
torchjd/torchjd pytorch

Tasks

Multi-Task LearningPrognosisRecommendation SystemsSurvey

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey

2024-12-18 · Yichen Li, Haozhao Wang, Wenchao Xu, Tianzhe Xiao 외

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high re…

Continual Learning

Advances in 3D Neural Stylization: A Survey

2023-11-30 · Yingshu Chen, Guocheng Shao, Ka Chun Shum, Binh-Son Hua 외

Modern artificial intelligence offers a novel and transformative approach to creating digital art across diverse styles and modalities like images, videos and 3D data, unleashing the power of creativity and revolutionizi…

NavigateNeural StylizationStyle TransferSurvey

Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models

2024-08-04 · Yulei Qin, Yuncheng Yang, Pengcheng Guo, Gang Li 외

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not b…

CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models

2024-01-06 · Yaojia LV, Haojie Pan, Zekun Wang, Jiafeng Liang 외

Cognitive dynamics are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) reveal their potential for cognitive simulation. However, these LLM-based cognitive studies …

Addressing the Curse of Scenario and Task Generalization in AI-6G: A Multi-Modal Paradigm

2025-04-07 · Tianyu Jiao, Zhuoran Xiao, Yin Xu, Chenhui Ye 외

Existing works on machine learning (ML)-empowered wireless communication primarily focus on monolithic scenarios and single tasks. However, with the blooming growth of communication task classes coupled with various task…