A Secure Aggregation for Federated Learning on Long-Tailed Data

A Secure Aggregation for Federated Learning on Long-Tailed Data

As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-07
Hauptverfasser: Jiang, Yanna, Ma, Baihe, Wang, Xu, Yu, Guangsheng, Sun, Caijun, Ni, Wei, Liu, Ren Ping
Format: Artikel
Sprache:eng
Schlagworte:
Federated learning
Nodes
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 Jiang, Yanna
Ma, Baihe
Wang, Xu
Yu, Guangsheng
Sun, Caijun
Ni, Wei
Liu, Ren Ping
description As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2838880219</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2838880219</sourcerecordid><originalsourceid>FETCH-proquest_journals_28388802193</originalsourceid><addsrcrecordid>eNqNikEKwjAQAIMgWLR_CHgupBur8SRFLR56s_ey2G1oKYlu0v_bgw_wNDAzK5GA1nlmDgAbkYYwKqXgeIKi0Im4lPJJr5lJltYyWYyDd7L3LCvqiDFSJ2tCdoOzcim1dzZrcJgWf8OIO7HucQqU_rgV--reXB_Zm_1nphDb0c_sltSC0cYYBflZ_3d9AW24N5g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2838880219</pqid></control><display><type>article</type><title>A Secure Aggregation for Federated Learning on Long-Tailed Data</title><source>Free E- Journals</source><creator>Jiang, Yanna ; Ma, Baihe ; Wang, Xu ; Yu, Guangsheng ; Sun, Caijun ; Ni, Wei ; Liu, Ren Ping</creator><creatorcontrib>Jiang, Yanna ; Ma, Baihe ; Wang, Xu ; Yu, Guangsheng ; Sun, Caijun ; Ni, Wei ; Liu, Ren Ping</creatorcontrib><description>As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Federated learning ; Nodes</subject><ispartof>arXiv.org, 2023-07</ispartof><rights>2023. 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>776,780</link.rule.ids></links><search><creatorcontrib>Jiang, Yanna</creatorcontrib><creatorcontrib>Ma, Baihe</creatorcontrib><creatorcontrib>Wang, Xu</creatorcontrib><creatorcontrib>Yu, Guangsheng</creatorcontrib><creatorcontrib>Sun, Caijun</creatorcontrib><creatorcontrib>Ni, Wei</creatorcontrib><creatorcontrib>Liu, Ren Ping</creatorcontrib><title>A Secure Aggregation for Federated Learning on Long-Tailed Data</title><title>arXiv.org</title><description>As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.</description><subject>Federated learning</subject><subject>Nodes</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNikEKwjAQAIMgWLR_CHgupBur8SRFLR56s_ey2G1oKYlu0v_bgw_wNDAzK5GA1nlmDgAbkYYwKqXgeIKi0Im4lPJJr5lJltYyWYyDd7L3LCvqiDFSJ2tCdoOzcim1dzZrcJgWf8OIO7HucQqU_rgV--reXB_Zm_1nphDb0c_sltSC0cYYBflZ_3d9AW24N5g</recordid><startdate>20230717</startdate><enddate>20230717</enddate><creator>Jiang, Yanna</creator><creator>Ma, Baihe</creator><creator>Wang, Xu</creator><creator>Yu, Guangsheng</creator><creator>Sun, Caijun</creator><creator>Ni, Wei</creator><creator>Liu, Ren Ping</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>20230717</creationdate><title>A Secure Aggregation for Federated Learning on Long-Tailed Data</title><author>Jiang, Yanna ; Ma, Baihe ; Wang, Xu ; Yu, Guangsheng ; Sun, Caijun ; Ni, Wei ; Liu, Ren Ping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28388802193</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Federated learning</topic><topic>Nodes</topic><toplevel>online_resources</toplevel><creatorcontrib>Jiang, Yanna</creatorcontrib><creatorcontrib>Ma, Baihe</creatorcontrib><creatorcontrib>Wang, Xu</creatorcontrib><creatorcontrib>Yu, Guangsheng</creatorcontrib><creatorcontrib>Sun, Caijun</creatorcontrib><creatorcontrib>Ni, Wei</creatorcontrib><creatorcontrib>Liu, Ren Ping</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>Publicly Available Content Database</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>Jiang, Yanna</au><au>Ma, Baihe</au><au>Wang, Xu</au><au>Yu, Guangsheng</au><au>Sun, Caijun</au><au>Ni, Wei</au><au>Liu, Ren Ping</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Secure Aggregation for Federated Learning on Long-Tailed Data</atitle><jtitle>arXiv.org</jtitle><date>2023-07-17</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.</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, 2023-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2838880219
source Free E- Journals
subjects Federated learning
Nodes
title A Secure Aggregation for Federated Learning on Long-Tailed Data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T14%3A34%3A52IST&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=A%20Secure%20Aggregation%20for%20Federated%20Learning%20on%20Long-Tailed%20Data&rft.jtitle=arXiv.org&rft.au=Jiang,%20Yanna&rft.date=2023-07-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2838880219%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2838880219&rft_id=info:pmid/&rfr_iscdi=true