@inproceedings{meshgi-etal-2022-q,
title = "{Q}-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty",
author = "Meshgi, Kourosh and
Sadat Mirzaei, Maryam and
Sekine, Satoshi",
editor = "Gella, Spandana and
He, He and
Majumder, Bodhisattwa Prasad and
Can, Burcu and
Giunchiglia, Eleonora and
Cahyawijaya, Samuel and
Min, Sewon and
Mozes, Maximilian and
Li, Xiang Lorraine and
Augenstein, Isabelle and
Rogers, Anna and
Cho, Kyunghyun and
Grefenstette, Edward and
Rimell, Laura and
Dyer, Chris",
booktitle = "Proceedings of the 7th Workshop on Representation Learning for NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.repl4nlp-1.2",
doi = "10.18653/v1/2022.repl4nlp-1.2",
pages = "9--19",
abstract = "Simultaneous training of a multi-task learning network on different domains or tasks is not always straightforward. It could lead to inferior performance or generalization compared to the corresponding single-task networks. An effective training scheduling method is deemed necessary to maximize the benefits of multi-task learning. Traditional schedulers follow a heuristic or prefixed strategy, ignoring the relation of the tasks, their sample complexities, and the state of the emergent shared features. We proposed a deep Q-Learning Scheduler (QLS) that monitors the state of the tasks and the shared features using a novel histogram of task uncertainty, and through trial-and-error, learns an optimal policy for task scheduling. Extensive experiments on multi-domain and multi-task settings with various task difficulty profiles have been conducted, the proposed method is benchmarked against other schedulers, its superior performance has been demonstrated, and results are discussed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meshgi-etal-2022-q">
<titleInfo>
<title>Q-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kourosh</namePart>
<namePart type="family">Meshgi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Sadat Mirzaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Sekine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bodhisattwa</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleonora</namePart>
<namePart type="family">Giunchiglia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Cahyawijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sewon</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Mozes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="given">Lorraine</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rimell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Simultaneous training of a multi-task learning network on different domains or tasks is not always straightforward. It could lead to inferior performance or generalization compared to the corresponding single-task networks. An effective training scheduling method is deemed necessary to maximize the benefits of multi-task learning. Traditional schedulers follow a heuristic or prefixed strategy, ignoring the relation of the tasks, their sample complexities, and the state of the emergent shared features. We proposed a deep Q-Learning Scheduler (QLS) that monitors the state of the tasks and the shared features using a novel histogram of task uncertainty, and through trial-and-error, learns an optimal policy for task scheduling. Extensive experiments on multi-domain and multi-task settings with various task difficulty profiles have been conducted, the proposed method is benchmarked against other schedulers, its superior performance has been demonstrated, and results are discussed.</abstract>
<identifier type="citekey">meshgi-etal-2022-q</identifier>
<identifier type="doi">10.18653/v1/2022.repl4nlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2022.repl4nlp-1.2</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>9</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Q-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty
%A Meshgi, Kourosh
%A Sadat Mirzaei, Maryam
%A Sekine, Satoshi
%Y Gella, Spandana
%Y He, He
%Y Majumder, Bodhisattwa Prasad
%Y Can, Burcu
%Y Giunchiglia, Eleonora
%Y Cahyawijaya, Samuel
%Y Min, Sewon
%Y Mozes, Maximilian
%Y Li, Xiang Lorraine
%Y Augenstein, Isabelle
%Y Rogers, Anna
%Y Cho, Kyunghyun
%Y Grefenstette, Edward
%Y Rimell, Laura
%Y Dyer, Chris
%S Proceedings of the 7th Workshop on Representation Learning for NLP
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F meshgi-etal-2022-q
%X Simultaneous training of a multi-task learning network on different domains or tasks is not always straightforward. It could lead to inferior performance or generalization compared to the corresponding single-task networks. An effective training scheduling method is deemed necessary to maximize the benefits of multi-task learning. Traditional schedulers follow a heuristic or prefixed strategy, ignoring the relation of the tasks, their sample complexities, and the state of the emergent shared features. We proposed a deep Q-Learning Scheduler (QLS) that monitors the state of the tasks and the shared features using a novel histogram of task uncertainty, and through trial-and-error, learns an optimal policy for task scheduling. Extensive experiments on multi-domain and multi-task settings with various task difficulty profiles have been conducted, the proposed method is benchmarked against other schedulers, its superior performance has been demonstrated, and results are discussed.
%R 10.18653/v1/2022.repl4nlp-1.2
%U https://aclanthology.org/2022.repl4nlp-1.2
%U https://doi.org/10.18653/v1/2022.repl4nlp-1.2
%P 9-19
Markdown (Informal)
[Q-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty](https://aclanthology.org/2022.repl4nlp-1.2) (Meshgi et al., RepL4NLP 2022)
ACL