@inproceedings{padmakumar-etal-2022-exploring,
title = "Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning",
author = "Padmakumar, Vishakh and
Lausen, Leonard and
Ballesteros, Miguel and
Zha, Sheng and
He, He and
Karypis, George",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.183",
doi = "10.18653/v1/2022.naacl-main.183",
pages = "2542--2550",
abstract = "Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performance. In this work, we aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning. We find that, on average, increasing the scale of multi-task learning, in terms of the number of tasks, indeed results in better learned representations than smaller multi-task setups. However, if the target tasks are known ahead of time, then training on a smaller set of related tasks is competitive to the large-scale multi-task training at a reduced computational cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="padmakumar-etal-2022-exploring">
<titleInfo>
<title>Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishakh</namePart>
<namePart type="family">Padmakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonard</namePart>
<namePart type="family">Lausen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Ballesteros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Zha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Karypis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performance. In this work, we aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning. We find that, on average, increasing the scale of multi-task learning, in terms of the number of tasks, indeed results in better learned representations than smaller multi-task setups. However, if the target tasks are known ahead of time, then training on a smaller set of related tasks is competitive to the large-scale multi-task training at a reduced computational cost.</abstract>
<identifier type="citekey">padmakumar-etal-2022-exploring</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.183</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.183</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2542</start>
<end>2550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning
%A Padmakumar, Vishakh
%A Lausen, Leonard
%A Ballesteros, Miguel
%A Zha, Sheng
%A He, He
%A Karypis, George
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F padmakumar-etal-2022-exploring
%X Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performance. In this work, we aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning. We find that, on average, increasing the scale of multi-task learning, in terms of the number of tasks, indeed results in better learned representations than smaller multi-task setups. However, if the target tasks are known ahead of time, then training on a smaller set of related tasks is competitive to the large-scale multi-task training at a reduced computational cost.
%R 10.18653/v1/2022.naacl-main.183
%U https://aclanthology.org/2022.naacl-main.183
%U https://doi.org/10.18653/v1/2022.naacl-main.183
%P 2542-2550
Markdown (Informal)
[Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning](https://aclanthology.org/2022.naacl-main.183) (Padmakumar et al., NAACL 2022)
ACL
- Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, and George Karypis. 2022. Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2542–2550, Seattle, United States. Association for Computational Linguistics.