Inferring Sparse Kernel Combinations and Relevance Vectors: An Application to Subcellular Localization of Proteins
In this paper, we introduce two new formulations for multi-class multi-kernel relevance vector machines (m-RVMs) that explicitly lead to sparse solutions, both in samples and in number of kernels. This enables their application to large-scale multi-feature multinomial classification problems where t...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 582 |
|---|---|
| container_issue | |
| container_start_page | 577 |
| container_title | |
| container_volume | |
| creator | Damoulas, T. Ying, Y. Girolami, M.A. Campbell, C. |
| description | In this paper, we introduce two new formulations for multi-class multi-kernel relevance vector machines (m-RVMs) that explicitly lead to sparse solutions, both in samples and in number of kernels. This enables their application to large-scale multi-feature multinomial classification problems where there is an abundance of training samples, classes and feature spaces. The proposed methods are based on an expectation-maximization (EM) framework employing a multinomial probit likelihood and explicit pruning of non-relevant training samples. We demonstrate the methods on a low-dimensional artificial dataset. We then demonstrate the accuracy and sparsity of the method when applied to the challenging bioinformatics task of predicting protein subcellular localization. |
| doi_str_mv | 10.1109/ICMLA.2008.124 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4725032</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4725032</ieee_id><sourcerecordid>4725032</sourcerecordid><originalsourceid>FETCH-LOGICAL-c286t-67b8a39c935e9163c2626f35068aeeb4d89758e45681b3559ae6338881788a1c3</originalsourceid><addsrcrecordid>eNotjEtLAzEUhQNS0NZu3bjJH2jNY5K5cTcMPoojilW3JZPekUiaGZKpoL_eR10cDnzn4xByxtmSc2YuVvV9Uy0FY7DkojgiU1Zqo2TxkwmZ_nLDQHF5TOY5vzPGuNElV3BC0ip2mJKPb3Q92JSR3mGKGGjd71of7ej7mKmNW_qEAT9sdEhf0Y19ype0irQahuDdn0bHnq73rcMQ9sEm2vTOBv912PqOPqZ-RB_zKZl0NmSc__eMvFxfPde3i-bhZlVXzcIJ0ONCly1YaZyRCg3X0gktdCcV02AR22ILplSAhdLAW6mUsailBABeAlju5IycH349Im6G5Hc2fW6KUigmhfwG9wdalw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Inferring Sparse Kernel Combinations and Relevance Vectors: An Application to Subcellular Localization of Proteins</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Damoulas, T. ; Ying, Y. ; Girolami, M.A. ; Campbell, C.</creator><creatorcontrib>Damoulas, T. ; Ying, Y. ; Girolami, M.A. ; Campbell, C.</creatorcontrib><description>In this paper, we introduce two new formulations for multi-class multi-kernel relevance vector machines (m-RVMs) that explicitly lead to sparse solutions, both in samples and in number of kernels. This enables their application to large-scale multi-feature multinomial classification problems where there is an abundance of training samples, classes and feature spaces. The proposed methods are based on an expectation-maximization (EM) framework employing a multinomial probit likelihood and explicit pruning of non-relevant training samples. We demonstrate the methods on a low-dimensional artificial dataset. We then demonstrate the accuracy and sparsity of the method when applied to the challenging bioinformatics task of predicting protein subcellular localization.</description><identifier>ISBN: 0769534953</identifier><identifier>ISBN: 9780769534954</identifier><identifier>DOI: 10.1109/ICMLA.2008.124</identifier><identifier>LCCN: 2008908513</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bayesian methods ; Bioinformatics ; Extraterrestrial measurements ; Kernel ; Kernel combination ; Large-scale systems ; Machine learning ; Mathematics ; Optimization methods ; Protein engineering ; Protein subcellular localization ; Relevance vector machine ; Sparsity ; Support vector machines</subject><ispartof>2008 Seventh International Conference on Machine Learning and Applications, 2008, p.577-582</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c286t-67b8a39c935e9163c2626f35068aeeb4d89758e45681b3559ae6338881788a1c3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4725032$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4725032$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Damoulas, T.</creatorcontrib><creatorcontrib>Ying, Y.</creatorcontrib><creatorcontrib>Girolami, M.A.</creatorcontrib><creatorcontrib>Campbell, C.</creatorcontrib><title>Inferring Sparse Kernel Combinations and Relevance Vectors: An Application to Subcellular Localization of Proteins</title><title>2008 Seventh International Conference on Machine Learning and Applications</title><addtitle>ICMLA</addtitle><description>In this paper, we introduce two new formulations for multi-class multi-kernel relevance vector machines (m-RVMs) that explicitly lead to sparse solutions, both in samples and in number of kernels. This enables their application to large-scale multi-feature multinomial classification problems where there is an abundance of training samples, classes and feature spaces. The proposed methods are based on an expectation-maximization (EM) framework employing a multinomial probit likelihood and explicit pruning of non-relevant training samples. We demonstrate the methods on a low-dimensional artificial dataset. We then demonstrate the accuracy and sparsity of the method when applied to the challenging bioinformatics task of predicting protein subcellular localization.</description><subject>Bayesian methods</subject><subject>Bioinformatics</subject><subject>Extraterrestrial measurements</subject><subject>Kernel</subject><subject>Kernel combination</subject><subject>Large-scale systems</subject><subject>Machine learning</subject><subject>Mathematics</subject><subject>Optimization methods</subject><subject>Protein engineering</subject><subject>Protein subcellular localization</subject><subject>Relevance vector machine</subject><subject>Sparsity</subject><subject>Support vector machines</subject><isbn>0769534953</isbn><isbn>9780769534954</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotjEtLAzEUhQNS0NZu3bjJH2jNY5K5cTcMPoojilW3JZPekUiaGZKpoL_eR10cDnzn4xByxtmSc2YuVvV9Uy0FY7DkojgiU1Zqo2TxkwmZ_nLDQHF5TOY5vzPGuNElV3BC0ip2mJKPb3Q92JSR3mGKGGjd71of7ej7mKmNW_qEAT9sdEhf0Y19ype0irQahuDdn0bHnq73rcMQ9sEm2vTOBv912PqOPqZ-RB_zKZl0NmSc__eMvFxfPde3i-bhZlVXzcIJ0ONCly1YaZyRCg3X0gktdCcV02AR22ILplSAhdLAW6mUsailBABeAlju5IycH349Im6G5Hc2fW6KUigmhfwG9wdalw</recordid><startdate>20080101</startdate><enddate>20080101</enddate><creator>Damoulas, T.</creator><creator>Ying, Y.</creator><creator>Girolami, M.A.</creator><creator>Campbell, C.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20080101</creationdate><title>Inferring Sparse Kernel Combinations and Relevance Vectors: An Application to Subcellular Localization of Proteins</title><author>Damoulas, T. ; Ying, Y. ; Girolami, M.A. ; Campbell, C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c286t-67b8a39c935e9163c2626f35068aeeb4d89758e45681b3559ae6338881788a1c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Bayesian methods</topic><topic>Bioinformatics</topic><topic>Extraterrestrial measurements</topic><topic>Kernel</topic><topic>Kernel combination</topic><topic>Large-scale systems</topic><topic>Machine learning</topic><topic>Mathematics</topic><topic>Optimization methods</topic><topic>Protein engineering</topic><topic>Protein subcellular localization</topic><topic>Relevance vector machine</topic><topic>Sparsity</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>Damoulas, T.</creatorcontrib><creatorcontrib>Ying, Y.</creatorcontrib><creatorcontrib>Girolami, M.A.</creatorcontrib><creatorcontrib>Campbell, C.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Damoulas, T.</au><au>Ying, Y.</au><au>Girolami, M.A.</au><au>Campbell, C.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Inferring Sparse Kernel Combinations and Relevance Vectors: An Application to Subcellular Localization of Proteins</atitle><btitle>2008 Seventh International Conference on Machine Learning and Applications</btitle><stitle>ICMLA</stitle><date>2008-01-01</date><risdate>2008</risdate><spage>577</spage><epage>582</epage><pages>577-582</pages><isbn>0769534953</isbn><isbn>9780769534954</isbn><abstract>In this paper, we introduce two new formulations for multi-class multi-kernel relevance vector machines (m-RVMs) that explicitly lead to sparse solutions, both in samples and in number of kernels. This enables their application to large-scale multi-feature multinomial classification problems where there is an abundance of training samples, classes and feature spaces. The proposed methods are based on an expectation-maximization (EM) framework employing a multinomial probit likelihood and explicit pruning of non-relevant training samples. We demonstrate the methods on a low-dimensional artificial dataset. We then demonstrate the accuracy and sparsity of the method when applied to the challenging bioinformatics task of predicting protein subcellular localization.</abstract><pub>IEEE</pub><doi>10.1109/ICMLA.2008.124</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0769534953 |
| ispartof | 2008 Seventh International Conference on Machine Learning and Applications, 2008, p.577-582 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_4725032 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Bayesian methods Bioinformatics Extraterrestrial measurements Kernel Kernel combination Large-scale systems Machine learning Mathematics Optimization methods Protein engineering Protein subcellular localization Relevance vector machine Sparsity Support vector machines |
| title | Inferring Sparse Kernel Combinations and Relevance Vectors: An Application to Subcellular Localization of Proteins |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T03%3A42%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Inferring%20Sparse%20Kernel%20Combinations%20and%20Relevance%20Vectors:%20An%20Application%20to%20Subcellular%20Localization%20of%20Proteins&rft.btitle=2008%20Seventh%20International%20Conference%20on%20Machine%20Learning%20and%20Applications&rft.au=Damoulas,%20T.&rft.date=2008-01-01&rft.spage=577&rft.epage=582&rft.pages=577-582&rft.isbn=0769534953&rft.isbn_list=9780769534954&rft_id=info:doi/10.1109/ICMLA.2008.124&rft_dat=%3Cieee_6IE%3E4725032%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4725032&rfr_iscdi=true |