BanditMTL: Bandit-based Multi-task Learning for Text Classification
Yuren Mao, Zekai Wang, Weiwei Liu, Xuemin Lin, Wenbin Hu
Abstract
Task variance regularization, which can be used to improve the generalization of Multi-task Learning (MTL) models, remains unexplored in multi-task text classification. Accordingly, to fill this gap, this paper investigates how the task might be effectively regularized, and consequently proposes a multi-task learning method based on adversarial multi-armed bandit. The proposed method, named BanditMTL, regularizes the task variance by means of a mirror gradient ascent-descent algorithm. Adopting BanditMTL in the multi-task text classification context is found to achieve state-of-the-art performance. The results of extensive experiments back up our theoretical analysis and validate the superiority of our proposals.
BibTeX
@inproceedings{mao-etal-2021-banditmtl,
title = "{B}andit{MTL}: Bandit-based Multi-task Learning for Text Classification",
author = "Mao, Yuren and
Wang, Zekai and
Liu, Weiwei and
Lin, Xuemin and
Hu, Wenbin",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.428/",
doi = "10.18653/v1/2021.acl-long.428",
pages = "5506--5516"
}