Learning Task Sampling Policy for Multitask Learning
Dhanasekar Sundararaman, Henry Tsai, Kuang-Huei Lee, Iulia Turc, Lawrence Carin
Abstract
It has been shown that training multi-task models with auxiliary tasks can improve the target task quality through cross-task transfer. However, the importance of each auxiliary task to the primary task is likely not known a priori. While the importance weights of auxiliary tasks can be manually tuned, it becomes practically infeasible with the number of tasks scaling up. To address this, we propose a search method that automatically assigns importance weights. We formulate it as a reinforcement learning problem and learn a task sampling schedule based on the evaluation accuracy of the multi-task model. Our empirical evaluation on XNLI and GLUE shows that our method outperforms uniform sampling and the corresponding single-task baseline.
BibTeX
@inproceedings{sundararaman-etal-2021-learning-task,
title = "Learning Task Sampling Policy for Multitask Learning",
author = "Sundararaman, Dhanasekar and
Tsai, Henry and
Lee, Kuang-Huei and
Turc, Iulia and
Carin, Lawrence",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.375/",
doi = "10.18653/v1/2021.findings-emnlp.375",
pages = "4410--4415"
}