Dual-Balancing for Multi-Task Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Baijiong, Jiang, Weisen, Ye, Feiyang, Zhang, Yu, Chen, Pengguang, Chen, Ying-Cong, Liu, Shu, Tsang, Ivor W., Kwok, James T.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911286768435200
author Lin, Baijiong
Jiang, Weisen
Ye, Feiyang
Zhang, Yu
Chen, Pengguang
Chen, Ying-Cong
Liu, Shu
Tsang, Ivor W.
Kwok, James T.
author_facet Lin, Baijiong
Jiang, Weisen
Ye, Feiyang
Zhang, Yu
Chen, Pengguang
Chen, Ying-Cong
Liu, Shu
Tsang, Ivor W.
Kwok, James T.
contents Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among tasks often leads to performance compromises, and the balancing of tasks remains a significant challenge. In this paper, we propose Dual-Balancing Multi-Task Learning (DB-MTL) to achieve task balancing from both the loss and gradient perspectives. Specifically, DB-MTL achieves loss-scale balancing by performing logarithm transformation on each task loss, and rescales gradient magnitudes by normalizing all task gradients to comparable magnitudes using the maximum gradient norm. Extensive experiments on a number of benchmark datasets demonstrate that DB-MTL consistently performs better than the current state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2308_12029
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Dual-Balancing for Multi-Task Learning
Lin, Baijiong
Jiang, Weisen
Ye, Feiyang
Zhang, Yu
Chen, Pengguang
Chen, Ying-Cong
Liu, Shu
Tsang, Ivor W.
Kwok, James T.
Machine Learning
Artificial Intelligence
Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among tasks often leads to performance compromises, and the balancing of tasks remains a significant challenge. In this paper, we propose Dual-Balancing Multi-Task Learning (DB-MTL) to achieve task balancing from both the loss and gradient perspectives. Specifically, DB-MTL achieves loss-scale balancing by performing logarithm transformation on each task loss, and rescales gradient magnitudes by normalizing all task gradients to comparable magnitudes using the maximum gradient norm. Extensive experiments on a number of benchmark datasets demonstrate that DB-MTL consistently performs better than the current state-of-the-art.
title Dual-Balancing for Multi-Task Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2308.12029