@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://preview.aclanthology.org/fix-sig-urls/2021.acl-long.428/",
    doi = "10.18653/v1/2021.acl-long.428",
    pages = "5506--5516",
    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."
}