Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Dong, Yu, Yanxuan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.18038
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916715468685312
author Liu, Dong
Yu, Yanxuan
author_facet Liu, Dong
Yu, Yanxuan
contents Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18038
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MT2ST: Adaptive Multi-Task to Single-Task Learning
Liu, Dong
Yu, Yanxuan
Machine Learning
Efficient machine learning (ML) has become increasingly important as models grow larger and data volumes expand. In this work, we address the trade-off between generalization in multi-task learning (MTL) and precision in single-task learning (STL) by introducing the Multi-Task to Single-Task (MT2ST) framework. MT2ST is designed to enhance training efficiency and accuracy in multi-modal tasks, showcasing its value as a practical application of efficient ML.
title MT2ST: Adaptive Multi-Task to Single-Task Learning
topic Machine Learning
url https://arxiv.org/abs/2406.18038