Branched Multi-Task Networks: Deciding What Layers To Share

In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understand...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-08
Hauptverfasser: Vandenhende, Simon, Georgoulis, Stamatios, De Brabandere, Bert, Luc Van Gool
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Vandenhende, Simon
Georgoulis, Stamatios
De Brabandere, Bert
Luc Van Gool
description In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understandably, as the number of possible network configurations is combinatorially large, deciding what layers to share and where to branch out becomes cumbersome. Prior works have either relied on ad hoc methods to determine the level of layer sharing, which is suboptimal, or utilized neural architecture search techniques to establish the network design, which is considerably expensive. In this paper, we go beyond these limitations and propose an approach to automatically construct branched multi-task networks, by leveraging the employed tasks' affinities. Given a specific budget, i.e. number of learnable parameters, the proposed approach generates architectures, in which shallow layers are task-agnostic, whereas deeper ones gradually grow more task-specific. Extensive experimental analysis across numerous, diverse multi-tasking datasets shows that, for a given budget, our method consistently yields networks with the highest performance, while for a certain performance threshold it requires the least amount of learnable parameters.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2205103102</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2205103102</sourcerecordid><originalsourceid>FETCH-proquest_journals_22051031023</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdipKzEvOSE1R8C3NKcnUDUkszlbwSy0pzy_KLrZScElNzkzJzEtXCM9ILFHwSaxMLSpWCMlXCM5ILErlYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IyMDU0MDY0MDI2PiVAEAizk2Cg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2205103102</pqid></control><display><type>article</type><title>Branched Multi-Task Networks: Deciding What Layers To Share</title><source>Free E- Journals</source><creator>Vandenhende, Simon ; Georgoulis, Stamatios ; De Brabandere, Bert ; Luc Van Gool</creator><creatorcontrib>Vandenhende, Simon ; Georgoulis, Stamatios ; De Brabandere, Bert ; Luc Van Gool</creatorcontrib><description>In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understandably, as the number of possible network configurations is combinatorially large, deciding what layers to share and where to branch out becomes cumbersome. Prior works have either relied on ad hoc methods to determine the level of layer sharing, which is suboptimal, or utilized neural architecture search techniques to establish the network design, which is considerably expensive. In this paper, we go beyond these limitations and propose an approach to automatically construct branched multi-task networks, by leveraging the employed tasks' affinities. Given a specific budget, i.e. number of learnable parameters, the proposed approach generates architectures, in which shallow layers are task-agnostic, whereas deeper ones gradually grow more task-specific. Extensive experimental analysis across numerous, diverse multi-tasking datasets shows that, for a given budget, our method consistently yields networks with the highest performance, while for a certain performance threshold it requires the least amount of learnable parameters.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Machine learning ; Neural networks</subject><ispartof>arXiv.org, 2020-08</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Vandenhende, Simon</creatorcontrib><creatorcontrib>Georgoulis, Stamatios</creatorcontrib><creatorcontrib>De Brabandere, Bert</creatorcontrib><creatorcontrib>Luc Van Gool</creatorcontrib><title>Branched Multi-Task Networks: Deciding What Layers To Share</title><title>arXiv.org</title><description>In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understandably, as the number of possible network configurations is combinatorially large, deciding what layers to share and where to branch out becomes cumbersome. Prior works have either relied on ad hoc methods to determine the level of layer sharing, which is suboptimal, or utilized neural architecture search techniques to establish the network design, which is considerably expensive. In this paper, we go beyond these limitations and propose an approach to automatically construct branched multi-task networks, by leveraging the employed tasks' affinities. Given a specific budget, i.e. number of learnable parameters, the proposed approach generates architectures, in which shallow layers are task-agnostic, whereas deeper ones gradually grow more task-specific. Extensive experimental analysis across numerous, diverse multi-tasking datasets shows that, for a given budget, our method consistently yields networks with the highest performance, while for a certain performance threshold it requires the least amount of learnable parameters.</description><subject>Machine learning</subject><subject>Neural networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdipKzEvOSE1R8C3NKcnUDUkszlbwSy0pzy_KLrZScElNzkzJzEtXCM9ILFHwSaxMLSpWCMlXCM5ILErlYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IyMDU0MDY0MDI2PiVAEAizk2Cg</recordid><startdate>20200813</startdate><enddate>20200813</enddate><creator>Vandenhende, Simon</creator><creator>Georgoulis, Stamatios</creator><creator>De Brabandere, Bert</creator><creator>Luc Van Gool</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200813</creationdate><title>Branched Multi-Task Networks: Deciding What Layers To Share</title><author>Vandenhende, Simon ; Georgoulis, Stamatios ; De Brabandere, Bert ; Luc Van Gool</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_22051031023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Machine learning</topic><topic>Neural networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Vandenhende, Simon</creatorcontrib><creatorcontrib>Georgoulis, Stamatios</creatorcontrib><creatorcontrib>De Brabandere, Bert</creatorcontrib><creatorcontrib>Luc Van Gool</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Vandenhende, Simon</au><au>Georgoulis, Stamatios</au><au>De Brabandere, Bert</au><au>Luc Van Gool</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Branched Multi-Task Networks: Deciding What Layers To Share</atitle><jtitle>arXiv.org</jtitle><date>2020-08-13</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>In the context of multi-task learning, neural networks with branched architectures have often been employed to jointly tackle the tasks at hand. Such ramified networks typically start with a number of shared layers, after which different tasks branch out into their own sequence of layers. Understandably, as the number of possible network configurations is combinatorially large, deciding what layers to share and where to branch out becomes cumbersome. Prior works have either relied on ad hoc methods to determine the level of layer sharing, which is suboptimal, or utilized neural architecture search techniques to establish the network design, which is considerably expensive. In this paper, we go beyond these limitations and propose an approach to automatically construct branched multi-task networks, by leveraging the employed tasks' affinities. Given a specific budget, i.e. number of learnable parameters, the proposed approach generates architectures, in which shallow layers are task-agnostic, whereas deeper ones gradually grow more task-specific. Extensive experimental analysis across numerous, diverse multi-tasking datasets shows that, for a given budget, our method consistently yields networks with the highest performance, while for a certain performance threshold it requires the least amount of learnable parameters.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2205103102
source Free E- Journals
subjects Machine learning
Neural networks
title Branched Multi-Task Networks: Deciding What Layers To Share
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T04%3A40%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Branched%20Multi-Task%20Networks:%20Deciding%20What%20Layers%20To%20Share&rft.jtitle=arXiv.org&rft.au=Vandenhende,%20Simon&rft.date=2020-08-13&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2205103102%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2205103102&rft_id=info:pmid/&rfr_iscdi=true