MetaWeighting: Learning to Weight Tasks in Multi-Task Learning
Yuren Mao, Zekai Wang, Weiwei Liu, Xuemin Lin, Pengtao Xie
Abstract
Task weighting, which assigns weights on the including tasks during training, significantly matters the performance of Multi-task Learning (MTL); thus, recently, there has been an explosive interest in it. However, existing task weighting methods assign weights only based on the training loss, while ignoring the gap between the training loss and generalization loss. It degenerates MTL’s performance. To address this issue, the present paper proposes a novel task weighting algorithm, which automatically weights the tasks via a learning-to-learn paradigm, referred to as MetaWeighting. Extensive experiments are conducted to validate the superiority of our proposed method in multi-task text classification.
BibTeX
@inproceedings{mao-etal-2022-metaweighting,
title = "{M}eta{W}eighting: Learning to Weight Tasks in Multi-Task Learning",
author = "Mao, Yuren and
Wang, Zekai and
Liu, Weiwei and
Lin, Xuemin and
Xie, Pengtao",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.271/",
doi = "10.18653/v1/2022.findings-acl.271",
pages = "3436--3448"
}