Task’s Choice: Pruning-Based Feature Sharing (PBFS) for Multi-Task Learning

In most of the existing multi-task learning (MTL) models, multiple tasks’ public information is learned by sharing parameters across hidden layers, such as hard sharing, soft sharing, and hierarchical sharing. One promising approach is to introduce model pruning into information learning, such as sp...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Ying, Yu, Jiong, Zhao, Yutong, Chen, Jiaying, Du, Xusheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947268/
https://www.ncbi.nlm.nih.gov/pubmed/35327942
http://dx.doi.org/10.3390/e24030432

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947268/
https://www.ncbi.nlm.nih.gov/pubmed/35327942
http://dx.doi.org/10.3390/e24030432

Ejemplares similares