Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations
Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.
Gespeichert in:
| Veröffentlicht in: | IEEE software 2024-01, Vol.41 (1), p.87-97 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 97 |
|---|---|
| container_issue | 1 |
| container_start_page | 87 |
| container_title | IEEE software |
| container_volume | 41 |
| creator | Aslansefat, Koorosh Hashemian, Mojgan Walker, Martin Akram, Mohammed Naveed Sorokos, Ioannis Papadopoulos, Yiannis |
| description | Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains. |
| doi_str_mv | 10.1109/MS.2023.3321282 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10272255</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10272255</ieee_id><sourcerecordid>2904665490</sourcerecordid><originalsourceid>FETCH-LOGICAL-c244t-d8ff10582ba83e7f0d1839cf8bab0bc8f89fd52cee1f9c17cb3b4b26d22a97e83</originalsourceid><addsrcrecordid>eNpNkM9LwzAYhoMoOKdnLx4KnrvlV9fE2zamDlo8VPEYkjTZMms7mwy2_97W7uDpg5fneT94AbhHcIIQ5NO8mGCIyYQQjDDDF2CEOEljiji9BCOYUhinNOHX4Mb7HYQwQQSOwHZ13FfS1a7eRItK6q9o0RyNjz5d2EYyKvJ1tnqKiiCD88FpWUV5U5oqnm_qpg-idR1Mu29NkMpVLpwGM2t69K-77tSm9rfgysrKm7vzHYOP59X78jXO3l7Wy3kWa0xpiEtmLYIJw0oyYlILS8QI15YpqaDSzDJuywRrY5DlGqVaEUUVnpUYS54aRsbgcejdt83Pwfggds2hrbuXAnNIZ7OEcthR04HSbeN9a6zYt-5btieBoOjnFHkh-jnFec7OeBgMZ4z5R-MU4yQhv78MccU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2904665490</pqid></control><display><type>article</type><title>Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations</title><source>IEEE Electronic Library (IEL)</source><creator>Aslansefat, Koorosh ; Hashemian, Mojgan ; Walker, Martin ; Akram, Mohammed Naveed ; Sorokos, Ioannis ; Papadopoulos, Yiannis</creator><creatorcontrib>Aslansefat, Koorosh ; Hashemian, Mojgan ; Walker, Martin ; Akram, Mohammed Naveed ; Sorokos, Ioannis ; Papadopoulos, Yiannis</creatorcontrib><description>Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.</description><identifier>ISSN: 0740-7459</identifier><identifier>EISSN: 1937-4194</identifier><identifier>DOI: 10.1109/MS.2023.3321282</identifier><identifier>CODEN: IESOEG</identifier><language>eng</language><publisher>Los Alamitos: IEEE</publisher><subject>Closed box ; Data models ; Gaussian distribution ; Machine learning ; Perturbation methods ; Predictive models ; Statistical models ; Training</subject><ispartof>IEEE software, 2024-01, Vol.41 (1), p.87-97</ispartof><rights>Copyright IEEE Computer Society 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c244t-d8ff10582ba83e7f0d1839cf8bab0bc8f89fd52cee1f9c17cb3b4b26d22a97e83</cites><orcidid>0000-0001-7007-5153 ; 0000-0003-2704-8381 ; 0000-0002-6793-3775 ; 0000-0001-9318-8177 ; 0000-0002-3035-1341</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10272255$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10272255$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Aslansefat, Koorosh</creatorcontrib><creatorcontrib>Hashemian, Mojgan</creatorcontrib><creatorcontrib>Walker, Martin</creatorcontrib><creatorcontrib>Akram, Mohammed Naveed</creatorcontrib><creatorcontrib>Sorokos, Ioannis</creatorcontrib><creatorcontrib>Papadopoulos, Yiannis</creatorcontrib><title>Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations</title><title>IEEE software</title><addtitle>S-M</addtitle><description>Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.</description><subject>Closed box</subject><subject>Data models</subject><subject>Gaussian distribution</subject><subject>Machine learning</subject><subject>Perturbation methods</subject><subject>Predictive models</subject><subject>Statistical models</subject><subject>Training</subject><issn>0740-7459</issn><issn>1937-4194</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkM9LwzAYhoMoOKdnLx4KnrvlV9fE2zamDlo8VPEYkjTZMms7mwy2_97W7uDpg5fneT94AbhHcIIQ5NO8mGCIyYQQjDDDF2CEOEljiji9BCOYUhinNOHX4Mb7HYQwQQSOwHZ13FfS1a7eRItK6q9o0RyNjz5d2EYyKvJ1tnqKiiCD88FpWUV5U5oqnm_qpg-idR1Mu29NkMpVLpwGM2t69K-77tSm9rfgysrKm7vzHYOP59X78jXO3l7Wy3kWa0xpiEtmLYIJw0oyYlILS8QI15YpqaDSzDJuywRrY5DlGqVaEUUVnpUYS54aRsbgcejdt83Pwfggds2hrbuXAnNIZ7OEcthR04HSbeN9a6zYt-5btieBoOjnFHkh-jnFec7OeBgMZ4z5R-MU4yQhv78MccU</recordid><startdate>202401</startdate><enddate>202401</enddate><creator>Aslansefat, Koorosh</creator><creator>Hashemian, Mojgan</creator><creator>Walker, Martin</creator><creator>Akram, Mohammed Naveed</creator><creator>Sorokos, Ioannis</creator><creator>Papadopoulos, Yiannis</creator><general>IEEE</general><general>IEEE Computer Society</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope><orcidid>https://orcid.org/0000-0001-7007-5153</orcidid><orcidid>https://orcid.org/0000-0003-2704-8381</orcidid><orcidid>https://orcid.org/0000-0002-6793-3775</orcidid><orcidid>https://orcid.org/0000-0001-9318-8177</orcidid><orcidid>https://orcid.org/0000-0002-3035-1341</orcidid></search><sort><creationdate>202401</creationdate><title>Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations</title><author>Aslansefat, Koorosh ; Hashemian, Mojgan ; Walker, Martin ; Akram, Mohammed Naveed ; Sorokos, Ioannis ; Papadopoulos, Yiannis</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c244t-d8ff10582ba83e7f0d1839cf8bab0bc8f89fd52cee1f9c17cb3b4b26d22a97e83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Closed box</topic><topic>Data models</topic><topic>Gaussian distribution</topic><topic>Machine learning</topic><topic>Perturbation methods</topic><topic>Predictive models</topic><topic>Statistical models</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Aslansefat, Koorosh</creatorcontrib><creatorcontrib>Hashemian, Mojgan</creatorcontrib><creatorcontrib>Walker, Martin</creatorcontrib><creatorcontrib>Akram, Mohammed Naveed</creatorcontrib><creatorcontrib>Sorokos, Ioannis</creatorcontrib><creatorcontrib>Papadopoulos, Yiannis</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>IEEE software</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Aslansefat, Koorosh</au><au>Hashemian, Mojgan</au><au>Walker, Martin</au><au>Akram, Mohammed Naveed</au><au>Sorokos, Ioannis</au><au>Papadopoulos, Yiannis</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations</atitle><jtitle>IEEE software</jtitle><stitle>S-M</stitle><date>2024-01</date><risdate>2024</risdate><volume>41</volume><issue>1</issue><spage>87</spage><epage>97</epage><pages>87-97</pages><issn>0740-7459</issn><eissn>1937-4194</eissn><coden>IESOEG</coden><abstract>Explainability is a key aspect of improving trustworthiness. We therefore propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.</abstract><cop>Los Alamitos</cop><pub>IEEE</pub><doi>10.1109/MS.2023.3321282</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0001-7007-5153</orcidid><orcidid>https://orcid.org/0000-0003-2704-8381</orcidid><orcidid>https://orcid.org/0000-0002-6793-3775</orcidid><orcidid>https://orcid.org/0000-0001-9318-8177</orcidid><orcidid>https://orcid.org/0000-0002-3035-1341</orcidid></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0740-7459 |
| ispartof | IEEE software, 2024-01, Vol.41 (1), p.87-97 |
| issn | 0740-7459 1937-4194 |
| language | eng |
| recordid | cdi_ieee_primary_10272255 |
| source | IEEE Electronic Library (IEL) |
| subjects | Closed box Data models Gaussian distribution Machine learning Perturbation methods Predictive models Statistical models Training |
| title | Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T04%3A48%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Explaining%20Black%20Boxes%20With%20a%20SMILE:%20Statistical%20Model-Agnostic%20Interpretability%20With%20Local%20Explanations&rft.jtitle=IEEE%20software&rft.au=Aslansefat,%20Koorosh&rft.date=2024-01&rft.volume=41&rft.issue=1&rft.spage=87&rft.epage=97&rft.pages=87-97&rft.issn=0740-7459&rft.eissn=1937-4194&rft.coden=IESOEG&rft_id=info:doi/10.1109/MS.2023.3321282&rft_dat=%3Cproquest_RIE%3E2904665490%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2904665490&rft_id=info:pmid/&rft_ieee_id=10272255&rfr_iscdi=true |