explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2019-10 |
|---|---|
| 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 | Spinner, Thilo Schlegel, Udo Schäfer, Hanna El-Assady, Mennatallah |
| description | We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions. |
| doi_str_mv | 10.48550/arxiv.1908.00087 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1908_00087</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2267999254</sourcerecordid><originalsourceid>FETCH-LOGICAL-a524-b2a70f032ab42a32487721ac2e0f1d42161aa2490cf4131c15c9664e954f87873</originalsourceid><addsrcrecordid>eNotkEFLAzEUhIMgWGp_gCcDnrcmL8km8baUVgsVL0W8La9pVlO32ZrdavvvXVtPA8PMwDeE3HA2lkYpdo_pEL7H3DIzZowZfUEGIATPjAS4IqO23fQ25BqUEgPy5g-7uphHnx5oQV9Du8eaFhHrYxdcS2cJt_6nSZ-0ahKdx84ndF349hTjmk77LoaIq9rTZ3QfIXq68JhiiO_X5LLCuvWjfx2S5Wy6nDxli5fH-aRYZKhAZitAzSomAFcSUIA0WgNHB55VfC2B5xwRpGWuklxwx5WzeS69VbIy2mgxJLfn2RN2uUthi-lY_uGXJ_w-cXdO7FLztfdtV26afeoJ2xL6G6y1oKT4Bem8XBQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2267999254</pqid></control><display><type>article</type><title>explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Spinner, Thilo ; Schlegel, Udo ; Schäfer, Hanna ; El-Assady, Mennatallah</creator><creatorcontrib>Spinner, Thilo ; Schlegel, Udo ; Schäfer, Hanna ; El-Assady, Mennatallah</creatorcontrib><description>We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1908.00087</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Analytics ; Artificial intelligence ; Computer Science - Artificial Intelligence ; Computer Science - Human-Computer Interaction ; Computer Science - Learning ; Explainable artificial intelligence ; Interactive systems ; Iterative methods ; Machine learning ; Monitoring ; Steering mechanisms ; Workflow</subject><ispartof>arXiv.org, 2019-10</ispartof><rights>2019. 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><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,786,887,27934</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.1908.00087$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1109/TVCG.2019.2934629$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Spinner, Thilo</creatorcontrib><creatorcontrib>Schlegel, Udo</creatorcontrib><creatorcontrib>Schäfer, Hanna</creatorcontrib><creatorcontrib>El-Assady, Mennatallah</creatorcontrib><title>explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning</title><title>arXiv.org</title><description>We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.</description><subject>Analytics</subject><subject>Artificial intelligence</subject><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Human-Computer Interaction</subject><subject>Computer Science - Learning</subject><subject>Explainable artificial intelligence</subject><subject>Interactive systems</subject><subject>Iterative methods</subject><subject>Machine learning</subject><subject>Monitoring</subject><subject>Steering mechanisms</subject><subject>Workflow</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkEFLAzEUhIMgWGp_gCcDnrcmL8km8baUVgsVL0W8La9pVlO32ZrdavvvXVtPA8PMwDeE3HA2lkYpdo_pEL7H3DIzZowZfUEGIATPjAS4IqO23fQ25BqUEgPy5g-7uphHnx5oQV9Du8eaFhHrYxdcS2cJt_6nSZ-0ahKdx84ndF349hTjmk77LoaIq9rTZ3QfIXq68JhiiO_X5LLCuvWjfx2S5Wy6nDxli5fH-aRYZKhAZitAzSomAFcSUIA0WgNHB55VfC2B5xwRpGWuklxwx5WzeS69VbIy2mgxJLfn2RN2uUthi-lY_uGXJ_w-cXdO7FLztfdtV26afeoJ2xL6G6y1oKT4Bem8XBQ</recordid><startdate>20191007</startdate><enddate>20191007</enddate><creator>Spinner, Thilo</creator><creator>Schlegel, Udo</creator><creator>Schäfer, Hanna</creator><creator>El-Assady, Mennatallah</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><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20191007</creationdate><title>explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning</title><author>Spinner, Thilo ; Schlegel, Udo ; Schäfer, Hanna ; El-Assady, Mennatallah</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a524-b2a70f032ab42a32487721ac2e0f1d42161aa2490cf4131c15c9664e954f87873</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Analytics</topic><topic>Artificial intelligence</topic><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Human-Computer Interaction</topic><topic>Computer Science - Learning</topic><topic>Explainable artificial intelligence</topic><topic>Interactive systems</topic><topic>Iterative methods</topic><topic>Machine learning</topic><topic>Monitoring</topic><topic>Steering mechanisms</topic><topic>Workflow</topic><toplevel>online_resources</toplevel><creatorcontrib>Spinner, Thilo</creatorcontrib><creatorcontrib>Schlegel, Udo</creatorcontrib><creatorcontrib>Schäfer, Hanna</creatorcontrib><creatorcontrib>El-Assady, Mennatallah</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</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><collection>arXiv Computer Science</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Spinner, Thilo</au><au>Schlegel, Udo</au><au>Schäfer, Hanna</au><au>El-Assady, Mennatallah</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning</atitle><jtitle>arXiv.org</jtitle><date>2019-10-07</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1908.00087</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2019-10 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_1908_00087 |
| source | arXiv.org; Free E- Journals |
| subjects | Analytics Artificial intelligence Computer Science - Artificial Intelligence Computer Science - Human-Computer Interaction Computer Science - Learning Explainable artificial intelligence Interactive systems Iterative methods Machine learning Monitoring Steering mechanisms Workflow |
| title | explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-02T06%3A50%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=explAIner:%20A%20Visual%20Analytics%20Framework%20for%20Interactive%20and%20Explainable%20Machine%20Learning&rft.jtitle=arXiv.org&rft.au=Spinner,%20Thilo&rft.date=2019-10-07&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1908.00087&rft_dat=%3Cproquest_arxiv%3E2267999254%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2267999254&rft_id=info:pmid/&rfr_iscdi=true |