Class Prior Estimation from Positive and Unlabeled Data
We consider the problem of learning a classifier using only positive and unlabeled samples. In this setting, it is known that a classifier can be successfully learned if the class prior is available. However, in practice, the class prior is unknown and thus must be estimated from data. In this paper...
Saved in:
| Published in | IEICE Transactions on Information and Systems Vol. E97.D; no. 5; pp. 1358 - 1362 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
The Institute of Electronics, Information and Communication Engineers
2014
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | We consider the problem of learning a classifier using only positive and unlabeled samples. In this setting, it is known that a classifier can be successfully learned if the class prior is available. However, in practice, the class prior is unknown and thus must be estimated from data. In this paper, we propose a new method to estimate the class prior by partially matching the class-conditional density of the positive class to the input density. By performing this partial matching in terms of the Pearson divergence, which we estimate directly without density estimation via lower-bound maximization, we can obtain an analytical estimator of the class prior. We further show that an existing class prior estimation method can also be interpreted as performing partial matching under the Pearson divergence, but in an indirect manner. The superiority of our direct class prior estimation method is illustrated on several benchmark datasets. |
|---|---|
| AbstractList | We consider the problem of learning a classifier using only positive and unlabeled samples. In this setting, it is known that a classifier can be successfully learned if the class prior is available. However, in practice, the class prior is unknown and thus must be estimated from data. In this paper, we propose a new method to estimate the class prior by partially matching the class-conditional density of the positive class to the input density. By performing this partial matching in terms of the Pearson divergence, which we estimate directly without density estimation via lower-bound maximization, we can obtain an analytical estimator of the class prior. We further show that an existing class prior estimation method can also be interpreted as performing partial matching under the Pearson divergence, but in an indirect manner. The superiority of our direct class prior estimation method is illustrated on several benchmark datasets. |
| Author | SUGIYAMA, Masashi PLESSIS, Marthinus Christoffel DU |
| Author_xml | – sequence: 1 fullname: PLESSIS, Marthinus Christoffel DU organization: Department of Computer Science, Tokyo Institute of Technology – sequence: 2 fullname: SUGIYAMA, Masashi organization: Department of Computer Science, Tokyo Institute of Technology |
| BookMark | eNpdkLFOwzAQhi1UJNrCE7BkZEmwY1-cjKgtUKkSHehsXRIHXKV2sV0k3p5UhQqx3C3_95_um5CRdVYTcstoxqCU99GjDcZ22aKS2TxjHMoLMmZSQMp4wUZkTCtWpCXw_IpMQthSysqcwZjIWY8hJGtvnE8WIZodRuNs0nm3S9YumGg-dYK2TTa2x1r3uk3mGPGaXHbYB33zs6dk87h4nT2nq5en5exhlTZQ0JjKjkPdlqIQVOa1aFkjK6m5FNhWdQVIWyqoyEsYRlc1SAFBUA0V1Fi1OfApuTv17r37OOgQ1c6ERvc9Wu0OQbFCMhhOMTZE-SnaeBeC153a--Ed_6UYVUdN6leTGjSpuTpqGqjlidqGiG_6zKCPpun1fwb-sOdM845eacu_ARmweNM |
| CitedBy_id | crossref_primary_10_1145_3575637_3575642 crossref_primary_10_1016_j_jisa_2024_103780 crossref_primary_10_1162_neco_a_01337 crossref_primary_10_1007_s44196_023_00373_9 crossref_primary_10_1007_s11634_021_00444_9 crossref_primary_10_1016_j_knosys_2020_106709 crossref_primary_10_1038_s44294_024_00011_5 crossref_primary_10_36469_jheor_2019_9727 crossref_primary_10_1007_s10994_020_05877_5 crossref_primary_10_1162_neco_a_01580 crossref_primary_10_3390_app122110763 crossref_primary_10_1016_j_asoc_2020_106986 crossref_primary_10_1002_1873_3468_12307 crossref_primary_10_1016_j_fmre_2022_09_019 crossref_primary_10_1109_TNNLS_2018_2870666 crossref_primary_10_1016_j_neunet_2018_05_001 crossref_primary_10_1007_s10115_022_01702_8 crossref_primary_10_1016_j_neucom_2019_08_001 crossref_primary_10_1214_20_AOAS1404 crossref_primary_10_1109_TMM_2018_2871421 crossref_primary_10_1145_3117807 crossref_primary_10_1002_int_22437 crossref_primary_10_1109_TKDE_2021_3119626 crossref_primary_10_1007_s10994_016_5604_6 crossref_primary_10_1016_j_media_2021_102185 |
| Cites_doi | 10.1007/978-0-387-21606-5 10.1109/TIT.2010.2068870 10.1007/978-1-4757-3264-1 10.1145/1401890.1401920 10.1109/ICDM.2008.49 10.1016/S1631-073X(03)00215-2 10.1109/TGRS.2010.2058578 |
| ContentType | Journal Article |
| Copyright | 2014 The Institute of Electronics, Information and Communication Engineers |
| Copyright_xml | – notice: 2014 The Institute of Electronics, Information and Communication Engineers |
| DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
| DOI | 10.1587/transinf.E97.D.1358 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Computer and Information Systems Abstracts |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 1745-1361 |
| EndPage | 1362 |
| ExternalDocumentID | 10_1587_transinf_E97_D_1358 article_transinf_E97_D_5_E97_D_1358_article_char_en |
| GroupedDBID | -~X 5GY ABQTQ ABZEH ACGFS ADNWM AENEX ALMA_UNASSIGNED_HOLDINGS CS3 DU5 EBS EJD F5P ICE JSF JSH KQ8 OK1 P2P RJT RZJ TN5 TQK ZKX 1TH AAYXX ABTAH AFFNX C1A CITATION CKLRP H13 RIG RYL VOH ZE2 ZY4 7SC 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c560t-7f35bd8464072b4d1c797e374ad9b95a0d0404285042f9ca05a540e595ba9d253 |
| ISSN | 0916-8532 |
| IngestDate | Thu Apr 11 21:51:35 EDT 2024 Fri Aug 23 02:39:00 EDT 2024 Wed Apr 05 14:01:09 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c560t-7f35bd8464072b4d1c797e374ad9b95a0d0404285042f9ca05a540e595ba9d253 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://www.jstage.jst.go.jp/article/transinf/E97.D/5/E97.D_1358/_article/-char/en |
| PQID | 1671556011 |
| PQPubID | 23500 |
| PageCount | 5 |
| ParticipantIDs | proquest_miscellaneous_1671556011 crossref_primary_10_1587_transinf_E97_D_1358 jstage_primary_article_transinf_E97_D_5_E97_D_1358_article_char_en |
| PublicationCentury | 2000 |
| PublicationDate | 2014-00-00 |
| PublicationDateYYYYMMDD | 2014-01-01 |
| PublicationDate_xml | – year: 2014 text: 2014-00-00 |
| PublicationDecade | 2010 |
| PublicationTitle | IEICE Transactions on Information and Systems |
| PublicationTitleAlternate | IEICE Trans. Inf. & Syst. |
| PublicationYear | 2014 |
| Publisher | The Institute of Electronics, Information and Communication Engineers |
| Publisher_xml | – name: The Institute of Electronics, Information and Communication Engineers |
| References | [8] W. Li, Q. Guo, and C. Elkan, “A positive and unlabeled learning algorithm for one-class classification of remote-sensing data,” IEEE Trans. Geosci. Remote Sen., vol.49, no.2, pp.717-725, 2011. [11] V. Vapnik, The Nature of Statistical Learning Theory, Springer, 2000. [5] T. Kanamori, S. Hido, and M. Sugiyama, “Efficient direct density ratio estimation for non-stationarity adaptation and outlier detection,” NIPS 21, pp.809-816, 2009. [7] A. Keziou, “Dual representation of φ-divergences and applications,” Comptes Rendus Mathématique, vol.336, no.10, pp.857-862, 2003. [10] M. Sugiyama, “Superfast-trainable multi-class probabilistic classifier by least-squares posterior fitting,” IEICE Trans. Inf. & Syst., vol.E93-D, no.10, pp.2690-2701, Oct. 2010. [2] C. Elkan and K. Noto, “Learning classifiers from only positive and unlabeled data,” 14th ACM SIGKDD, pp.213-220, 2008. [3] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, New York, NY, USA, 2001. [4] S. Hido, Y. Tsuboi, H. Kashima, M. Sugiyama, and T. Kanamori, “Inlier-based outlier detection via direct density ratio estimation,” ICDM 2008, pp.223-232, 2008. [9] X. Nguyen, M.J. Wainwright, and M.I. Jordan, “Estimating divergence functionals and the likelihood ratio by convex risk minimization,” IEEE Trans. Inf. Theory, vol.56, no.11, pp.5847-5861, 2010. [1] M.C. du Plessis and M. Sugiyama, “Semi-supervised learning of class balance under class-prior change by distribution matching,” ICML 2012, pp.823-830, 2012. [6] T. Kanamori, S. Hido, and M. Sugiyama, “A least-squares approach to direct importance estimation,” J. Machine Learning Research, vol.10, pp.1391-1445, July 2009. 11 1 2 3 4 5 6 7 8 9 10 |
| References_xml | – ident: 3 doi: 10.1007/978-0-387-21606-5 – ident: 9 doi: 10.1109/TIT.2010.2068870 – ident: 5 – ident: 11 doi: 10.1007/978-1-4757-3264-1 – ident: 1 – ident: 2 doi: 10.1145/1401890.1401920 – ident: 6 – ident: 4 doi: 10.1109/ICDM.2008.49 – ident: 7 doi: 10.1016/S1631-073X(03)00215-2 – ident: 10 – ident: 8 doi: 10.1109/TGRS.2010.2058578 |
| SSID | ssj0018215 ssib053832749 ssib002991706 ssib036429076 ssib036429077 ssib023157076 |
| Score | 2.2783906 |
| Snippet | We consider the problem of learning a classifier using only positive and unlabeled samples. In this setting, it is known that a classifier can be successfully... |
| SourceID | proquest crossref jstage |
| SourceType | Aggregation Database Publisher |
| StartPage | 1358 |
| SubjectTerms | class-prior change Classifiers Density Divergence divergence estimation Estimates Learning Matching Mathematical analysis Maximization outlier detection pearson divergence positive and unlabeled learning |
| Title | Class Prior Estimation from Positive and Unlabeled Data |
| URI | https://www.jstage.jst.go.jp/article/transinf/E97.D/5/E97.D_1358/_article/-char/en https://search.proquest.com/docview/1671556011 |
| Volume | E97.D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| ispartofPNX | IEICE Transactions on Information and Systems, 2014/05/01, Vol.E97.D(5), pp.1358-1362 |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwELdg8AAPfAwQ5UtG4m2kNHUcz4-wpdpgGkNqpb5FTpyMTixFbYoEfz0_x3YSWB8GL1Zr2VFyd7772ee7I-SN1joumdRY4mUURLlmQaZEZC5TZSNdchmVTbbP0_hoFn2c87mvd--iS-psmP_aGlfyP1xFH_hqomT_gbPtQ9GB3-AvWnAY7bV43FS03DtbLZarvQRr9dLdHDQhI2fNbawf1jswq8BsGBgNLteqD0iPk-ODxBSK8FXDG_eBS6da-7vK615ec6NHv5nLs2sX61N_XVSbtU9TUJYFFOmmczadL36qS2XHrk3ppv5Bgw3t9GeFYRzArlu1WVhNKSIehMxmUveqNJFieNiTGt5TjSGzOdqdmcXU8VYVzs0hyKT5bvQPm0cOu8n9hNmnn9PJ7OQknSbz6U1yawxdY251fvrS20EB_4rOkQw0y8WoQ2AM2y959X-LyGAOGPbtsnVM7Y9tUQxPEZfICi_9bssr_wF2bl8A759fNfoNkpk-IPfcFoS-t_L0kNy4ULvkvi_vQZ223yV3e7kqHxHRCBtthI12wkaNsFEvbBTCQltho0bYHpPZJJkeHAWu6kaQA_3WgSgZzzRgqUmdl0U6zIUUBROR0jKTXI009D42rRxNKXM14gqov-CSZ0rqMWdPyE61rIqnhOowhg0rgKrVfqQYV5lx0rI85yyWeRwPyFtPnvS7Ta6Smk0pqJl6aqagZnqYGmoOyAdLwnawW3l_D-a9Se0YE8UIpTEgrz35U2hS4x5TVbHcrNMwFgDXMQzes2uMeU7umEViT-NekJ16tSleAp_W2atGAn8D4w6L5w |
| link.rule.ids | 315,783,787,4031,27935,27936,27937 |
| linkProvider | Colorado Alliance of Research Libraries |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Class+Prior+Estimation+from+Positive+and+Unlabeled+Data&rft.jtitle=IEICE+transactions+on+information+and+systems&rft.au=Plessis%2C+Marthinus+Christoffel+Du&rft.au=Sugiyama%2C+Masashi&rft.date=2014&rft.issn=0916-8532&rft.eissn=1745-1361&rft.volume=E97.D&rft.issue=5&rft.spage=1358&rft.epage=1362&rft_id=info:doi/10.1587%2Ftransinf.E97.D.1358&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0916-8532&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0916-8532&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0916-8532&client=summon |