@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",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sundararaman-etal-2021-learning-task">
<titleInfo>
<title>Learning Task Sampling Policy for Multitask Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhanasekar</namePart>
<namePart type="family">Sundararaman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henry</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuang-Huei</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iulia</namePart>
<namePart type="family">Turc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Carin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sundararaman-etal-2021-learning-task</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.375</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.375</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4410</start>
<end>4415</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Task Sampling Policy for Multitask Learning
%A Sundararaman, Dhanasekar
%A Tsai, Henry
%A Lee, Kuang-Huei
%A Turc, Iulia
%A Carin, Lawrence
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F sundararaman-etal-2021-learning-task
%X 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.
%R 10.18653/v1/2021.findings-emnlp.375
%U https://aclanthology.org/2021.findings-emnlp.375
%U https://doi.org/10.18653/v1/2021.findings-emnlp.375
%P 4410-4415
Markdown (Informal)
[Learning Task Sampling Policy for Multitask Learning](https://aclanthology.org/2021.findings-emnlp.375) (Sundararaman et al., Findings 2021)
ACL
- Dhanasekar Sundararaman, Henry Tsai, Kuang-Huei Lee, Iulia Turc, and Lawrence Carin. 2021. Learning Task Sampling Policy for Multitask Learning. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4410–4415, Punta Cana, Dominican Republic. Association for Computational Linguistics.