Imbalanced Node Processing Method in Graph Neural Network Classification Task

In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, result...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Min, Jin, Siwen, Jin, Luo, Wang, Shuohan, Fang, Yu, Shi, Yuliang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Liu, Min
Jin, Siwen
Jin, Luo
Wang, Shuohan
Fang, Yu
Shi, Yuliang
description In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, resulting in suboptimal results in classification. Proposing a solution to the imbalance problem has become indispensable for the successful advancement of our downstream missions. Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task. thence, we introduce GHMC Loss into the graph neural networks to deal with difficult samples that are not marginal. Attenuate the loss contribution of marginal samples and simple samples. Experiments on multiple benchmarks show that our method can effectively deal with the class imbalance problem, and our method improves the accuracy by 3% compared to the traditional loss function.
doi_str_mv 10.48550/arxiv.2209.08514
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2209_08514</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2209_08514</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-e7cb0e72df7e5e06fa9c89a34dedb23dade9ca01641a01b6b7c8ffef9acab6513</originalsourceid><addsrcrecordid>eNotj7tOwzAYRr0woJYHYMIvkOAkvsRjFUGp1BaG7NFv-ze1msaVE25vTyhdvrN8OtIh5L5gOa-FYI-QvsNnXpZM56wWBb8lu83JQA-DRUf30SF9S9HiOIbhne5wOkRHw0DXCc4HusePBP2M6SumI216mH8-WJhCHGgL43FJbjz0I95duSDt81PbvGTb1_WmWW0zkIpnqKxhqErnFQpk0oO2tYaKO3SmrBw41BZYIXkxr5FG2dp79BosGCmKakEe_rWXnu6cwgnST_fX1V26ql-Kl0oK</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Imbalanced Node Processing Method in Graph Neural Network Classification Task</title><source>arXiv.org</source><creator>Liu, Min ; Jin, Siwen ; Jin, Luo ; Wang, Shuohan ; Fang, Yu ; Shi, Yuliang</creator><creatorcontrib>Liu, Min ; Jin, Siwen ; Jin, Luo ; Wang, Shuohan ; Fang, Yu ; Shi, Yuliang</creatorcontrib><description>In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, resulting in suboptimal results in classification. Proposing a solution to the imbalance problem has become indispensable for the successful advancement of our downstream missions. Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task. thence, we introduce GHMC Loss into the graph neural networks to deal with difficult samples that are not marginal. Attenuate the loss contribution of marginal samples and simple samples. Experiments on multiple benchmarks show that our method can effectively deal with the class imbalance problem, and our method improves the accuracy by 3% compared to the traditional loss function.</description><identifier>DOI: 10.48550/arxiv.2209.08514</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2022-09</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2209.08514$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2209.08514$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Liu, Min</creatorcontrib><creatorcontrib>Jin, Siwen</creatorcontrib><creatorcontrib>Jin, Luo</creatorcontrib><creatorcontrib>Wang, Shuohan</creatorcontrib><creatorcontrib>Fang, Yu</creatorcontrib><creatorcontrib>Shi, Yuliang</creatorcontrib><title>Imbalanced Node Processing Method in Graph Neural Network Classification Task</title><description>In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, resulting in suboptimal results in classification. Proposing a solution to the imbalance problem has become indispensable for the successful advancement of our downstream missions. Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task. thence, we introduce GHMC Loss into the graph neural networks to deal with difficult samples that are not marginal. Attenuate the loss contribution of marginal samples and simple samples. Experiments on multiple benchmarks show that our method can effectively deal with the class imbalance problem, and our method improves the accuracy by 3% compared to the traditional loss function.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj7tOwzAYRr0woJYHYMIvkOAkvsRjFUGp1BaG7NFv-ze1msaVE25vTyhdvrN8OtIh5L5gOa-FYI-QvsNnXpZM56wWBb8lu83JQA-DRUf30SF9S9HiOIbhne5wOkRHw0DXCc4HusePBP2M6SumI216mH8-WJhCHGgL43FJbjz0I95duSDt81PbvGTb1_WmWW0zkIpnqKxhqErnFQpk0oO2tYaKO3SmrBw41BZYIXkxr5FG2dp79BosGCmKakEe_rWXnu6cwgnST_fX1V26ql-Kl0oK</recordid><startdate>20220918</startdate><enddate>20220918</enddate><creator>Liu, Min</creator><creator>Jin, Siwen</creator><creator>Jin, Luo</creator><creator>Wang, Shuohan</creator><creator>Fang, Yu</creator><creator>Shi, Yuliang</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220918</creationdate><title>Imbalanced Node Processing Method in Graph Neural Network Classification Task</title><author>Liu, Min ; Jin, Siwen ; Jin, Luo ; Wang, Shuohan ; Fang, Yu ; Shi, Yuliang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-e7cb0e72df7e5e06fa9c89a34dedb23dade9ca01641a01b6b7c8ffef9acab6513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Min</creatorcontrib><creatorcontrib>Jin, Siwen</creatorcontrib><creatorcontrib>Jin, Luo</creatorcontrib><creatorcontrib>Wang, Shuohan</creatorcontrib><creatorcontrib>Fang, Yu</creatorcontrib><creatorcontrib>Shi, Yuliang</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Liu, Min</au><au>Jin, Siwen</au><au>Jin, Luo</au><au>Wang, Shuohan</au><au>Fang, Yu</au><au>Shi, Yuliang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Imbalanced Node Processing Method in Graph Neural Network Classification Task</atitle><date>2022-09-18</date><risdate>2022</risdate><abstract>In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, resulting in suboptimal results in classification. Proposing a solution to the imbalance problem has become indispensable for the successful advancement of our downstream missions. Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task. thence, we introduce GHMC Loss into the graph neural networks to deal with difficult samples that are not marginal. Attenuate the loss contribution of marginal samples and simple samples. Experiments on multiple benchmarks show that our method can effectively deal with the class imbalance problem, and our method improves the accuracy by 3% compared to the traditional loss function.</abstract><doi>10.48550/arxiv.2209.08514</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2209.08514
ispartof
issn
language eng
recordid cdi_arxiv_primary_2209_08514
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
title Imbalanced Node Processing Method in Graph Neural Network Classification Task
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T21%3A31%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Imbalanced%20Node%20Processing%20Method%20in%20Graph%20Neural%20Network%20Classification%20Task&rft.au=Liu,%20Min&rft.date=2022-09-18&rft_id=info:doi/10.48550/arxiv.2209.08514&rft_dat=%3Carxiv_GOX%3E2209_08514%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true