Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data
The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) clas...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-02 |
---|---|
Hauptverfasser: | , , , , |
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 | Yu, Bing Sun, Ke Wang, He Lin, Zhouchen Zhu, Zhanxing |
description | The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. In particular, we present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN, and experimentally, we conducted extensive evaluations on diverse datasets, verifying the simultaneous improvements in both classification and generation. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2413792667</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2413792667</sourcerecordid><originalsourceid>FETCH-proquest_journals_24137926673</originalsourceid><addsrcrecordid>eNqNjcuKAjEQRcOAoKj_UDDrhjbRbsdtj4-FC1FnLTV2ORMpE02lffy9jeje1eXA4dwP1dLG9JJhX-um6ors0zTVWa4HA9NS14JRxO5ugK6EKTkKGAmWtLXH4LfIfBvByh4qjujIVwILLzbaMyU_jvGXmKmEOWFw1v09IoV3ZW14h_wK1gAXG_9hfI0B4RsjdlRjhyzUfW5bfU7G62KW1LeniiRu9r4KdUM2ut8z-ZfOsty8Z90BvPpOOA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2413792667</pqid></control><display><type>article</type><title>Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data</title><source>Free E- Journals</source><creator>Yu, Bing ; Sun, Ke ; Wang, He ; Lin, Zhouchen ; Zhu, Zhanxing</creator><creatorcontrib>Yu, Bing ; Sun, Ke ; Wang, He ; Lin, Zhouchen ; Zhu, Zhanxing</creatorcontrib><description>The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. In particular, we present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN, and experimentally, we conducted extensive evaluations on diverse datasets, verifying the simultaneous improvements in both classification and generation.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Classification ; Classifiers ; Labels ; Machine learning</subject><ispartof>arXiv.org, 2024-02</ispartof><rights>2024. 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>Yu, Bing</creatorcontrib><creatorcontrib>Sun, Ke</creatorcontrib><creatorcontrib>Wang, He</creatorcontrib><creatorcontrib>Lin, Zhouchen</creatorcontrib><creatorcontrib>Zhu, Zhanxing</creatorcontrib><title>Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data</title><title>arXiv.org</title><description>The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. In particular, we present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN, and experimentally, we conducted extensive evaluations on diverse datasets, verifying the simultaneous improvements in both classification and generation.</description><subject>Classification</subject><subject>Classifiers</subject><subject>Labels</subject><subject>Machine learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjcuKAjEQRcOAoKj_UDDrhjbRbsdtj4-FC1FnLTV2ORMpE02lffy9jeje1eXA4dwP1dLG9JJhX-um6ors0zTVWa4HA9NS14JRxO5ugK6EKTkKGAmWtLXH4LfIfBvByh4qjujIVwILLzbaMyU_jvGXmKmEOWFw1v09IoV3ZW14h_wK1gAXG_9hfI0B4RsjdlRjhyzUfW5bfU7G62KW1LeniiRu9r4KdUM2ut8z-ZfOsty8Z90BvPpOOA</recordid><startdate>20240209</startdate><enddate>20240209</enddate><creator>Yu, Bing</creator><creator>Sun, Ke</creator><creator>Wang, He</creator><creator>Lin, Zhouchen</creator><creator>Zhu, Zhanxing</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>20240209</creationdate><title>Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data</title><author>Yu, Bing ; Sun, Ke ; Wang, He ; Lin, Zhouchen ; Zhu, Zhanxing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24137926673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Classification</topic><topic>Classifiers</topic><topic>Labels</topic><topic>Machine learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Yu, Bing</creatorcontrib><creatorcontrib>Sun, Ke</creatorcontrib><creatorcontrib>Wang, He</creatorcontrib><creatorcontrib>Lin, Zhouchen</creatorcontrib><creatorcontrib>Zhu, Zhanxing</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni)</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>Yu, Bing</au><au>Sun, Ke</au><au>Wang, He</au><au>Lin, Zhouchen</au><au>Zhu, Zhanxing</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data</atitle><jtitle>arXiv.org</jtitle><date>2024-02-09</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>The scarcity of class-labeled data is a ubiquitous bottleneck in many machine learning problems. While abundant unlabeled data typically exist and provide a potential solution, it is highly challenging to exploit them. In this paper, we address this problem by leveraging Positive-Unlabeled~(PU) classification and the conditional generation with extra unlabeled data \emph{simultaneously}. In particular, we present a novel training framework to jointly target both PU classification and conditional generation when exposed to extra data, especially out-of-distribution unlabeled data, by exploring the interplay between them: 1) enhancing the performance of PU classifiers with the assistance of a novel Classifier-Noise-Invariant Conditional GAN~(CNI-CGAN) that is robust to noisy labels, 2) leveraging extra data with predicted labels from a PU classifier to help the generation. Theoretically, we prove the optimal condition of CNI-CGAN, and experimentally, we conducted extensive evaluations on diverse datasets, verifying the simultaneous improvements in both classification and generation.</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, 2024-02 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2413792667 |
source | Free E- Journals |
subjects | Classification Classifiers Labels Machine learning |
title | Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T17%3A32%3A47IST&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=Classify%20and%20Generate%20Reciprocally:%20Simultaneous%20Positive-Unlabelled%20Learning%20and%20Conditional%20Generation%20with%20Extra%20Data&rft.jtitle=arXiv.org&rft.au=Yu,%20Bing&rft.date=2024-02-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2413792667%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2413792667&rft_id=info:pmid/&rfr_iscdi=true |