Melody: Generating and Visualizing Machine Learning Model Summary to Understand Data and Classifiers Together

With the increasing sophistication of machine learning models, there are growing trends of developing model explanation techniques that focus on only one instance (local explanation) to ensure faithfulness to the original model. While these techniques provide accurate model interpretability on vario...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chan, Gromit Yeuk-Yin, Bertini, Enrico, Nonato, Luis Gustavo, Barr, Brian, Silva, Claudio T
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Chan, Gromit Yeuk-Yin
Bertini, Enrico
Nonato, Luis Gustavo
Barr, Brian
Silva, Claudio T
description With the increasing sophistication of machine learning models, there are growing trends of developing model explanation techniques that focus on only one instance (local explanation) to ensure faithfulness to the original model. While these techniques provide accurate model interpretability on various data primitive (e.g., tabular, image, or text), a holistic Explainable Artificial Intelligence (XAI) experience also requires a global explanation of the model and dataset to enable sensemaking in different granularity. Thus, there is a vast potential in synergizing the model explanation and visual analytics approaches. In this paper, we present MELODY, an interactive algorithm to construct an optimal global overview of the model and data behavior by summarizing the local explanations using information theory. The result (i.e., an explanation summary) does not require additional learning models, restrictions of data primitives, or the knowledge of machine learning from the users. We also design MELODY UI, an interactive visual analytics system to demonstrate how the explanation summary connects the dots in various XAI tasks from a global overview to local inspections. We present three usage scenarios regarding tabular, image, and text classifications to illustrate how to generalize model interpretability of different data. Our experiments show that our approaches: (1) provides a better explanation summary compared to a straightforward information-theoretic summarization and (2) achieves a significant speedup in the end-to-end data modeling pipeline.
doi_str_mv 10.48550/arxiv.2007.10614
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2007_10614</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2007_10614</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-60642e31e5a97b23abd3b6a2cc00cc042d70061efc80f17dcbf670eeac3262e33</originalsourceid><addsrcrecordid>eNotj0FPhDAQhXvxYFZ_gKftHwCHFtrVm0FdTdh4kPVKhnbYbQLFFNa4_noBPUwm8ybv5X2M3SQQp5ssg1sM3-4rFgA6TkAl6SXrdtT29nzPt-Qp4Oj8gaO3_MMNJ2zdz3zv0BydJ14QBr8IvaWWv5-6DsOZjz3fe0thGGfjI464JOQtDoNr3PTgZX-g8Ujhil002A50_b9XrHx-KvOXqHjbvuYPRYRKp5EClQqSCWV4p2shsbayViiMAZgmFVbD1J4as4Em0dbUjdJAhEYKNRnliq3_Yhfe6jO4uWg1c1cLt_wFqfxUew</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Melody: Generating and Visualizing Machine Learning Model Summary to Understand Data and Classifiers Together</title><source>arXiv.org</source><creator>Chan, Gromit Yeuk-Yin ; Bertini, Enrico ; Nonato, Luis Gustavo ; Barr, Brian ; Silva, Claudio T</creator><creatorcontrib>Chan, Gromit Yeuk-Yin ; Bertini, Enrico ; Nonato, Luis Gustavo ; Barr, Brian ; Silva, Claudio T</creatorcontrib><description>With the increasing sophistication of machine learning models, there are growing trends of developing model explanation techniques that focus on only one instance (local explanation) to ensure faithfulness to the original model. While these techniques provide accurate model interpretability on various data primitive (e.g., tabular, image, or text), a holistic Explainable Artificial Intelligence (XAI) experience also requires a global explanation of the model and dataset to enable sensemaking in different granularity. Thus, there is a vast potential in synergizing the model explanation and visual analytics approaches. In this paper, we present MELODY, an interactive algorithm to construct an optimal global overview of the model and data behavior by summarizing the local explanations using information theory. The result (i.e., an explanation summary) does not require additional learning models, restrictions of data primitives, or the knowledge of machine learning from the users. We also design MELODY UI, an interactive visual analytics system to demonstrate how the explanation summary connects the dots in various XAI tasks from a global overview to local inspections. We present three usage scenarios regarding tabular, image, and text classifications to illustrate how to generalize model interpretability of different data. Our experiments show that our approaches: (1) provides a better explanation summary compared to a straightforward information-theoretic summarization and (2) achieves a significant speedup in the end-to-end data modeling pipeline.</description><identifier>DOI: 10.48550/arxiv.2007.10614</identifier><language>eng</language><subject>Computer Science - Human-Computer Interaction</subject><creationdate>2020-07</creationdate><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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2007.10614$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2007.10614$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chan, Gromit Yeuk-Yin</creatorcontrib><creatorcontrib>Bertini, Enrico</creatorcontrib><creatorcontrib>Nonato, Luis Gustavo</creatorcontrib><creatorcontrib>Barr, Brian</creatorcontrib><creatorcontrib>Silva, Claudio T</creatorcontrib><title>Melody: Generating and Visualizing Machine Learning Model Summary to Understand Data and Classifiers Together</title><description>With the increasing sophistication of machine learning models, there are growing trends of developing model explanation techniques that focus on only one instance (local explanation) to ensure faithfulness to the original model. While these techniques provide accurate model interpretability on various data primitive (e.g., tabular, image, or text), a holistic Explainable Artificial Intelligence (XAI) experience also requires a global explanation of the model and dataset to enable sensemaking in different granularity. Thus, there is a vast potential in synergizing the model explanation and visual analytics approaches. In this paper, we present MELODY, an interactive algorithm to construct an optimal global overview of the model and data behavior by summarizing the local explanations using information theory. The result (i.e., an explanation summary) does not require additional learning models, restrictions of data primitives, or the knowledge of machine learning from the users. We also design MELODY UI, an interactive visual analytics system to demonstrate how the explanation summary connects the dots in various XAI tasks from a global overview to local inspections. We present three usage scenarios regarding tabular, image, and text classifications to illustrate how to generalize model interpretability of different data. Our experiments show that our approaches: (1) provides a better explanation summary compared to a straightforward information-theoretic summarization and (2) achieves a significant speedup in the end-to-end data modeling pipeline.</description><subject>Computer Science - Human-Computer Interaction</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0FPhDAQhXvxYFZ_gKftHwCHFtrVm0FdTdh4kPVKhnbYbQLFFNa4_noBPUwm8ybv5X2M3SQQp5ssg1sM3-4rFgA6TkAl6SXrdtT29nzPt-Qp4Oj8gaO3_MMNJ2zdz3zv0BydJ14QBr8IvaWWv5-6DsOZjz3fe0thGGfjI464JOQtDoNr3PTgZX-g8Ujhil002A50_b9XrHx-KvOXqHjbvuYPRYRKp5EClQqSCWV4p2shsbayViiMAZgmFVbD1J4as4Em0dbUjdJAhEYKNRnliq3_Yhfe6jO4uWg1c1cLt_wFqfxUew</recordid><startdate>20200721</startdate><enddate>20200721</enddate><creator>Chan, Gromit Yeuk-Yin</creator><creator>Bertini, Enrico</creator><creator>Nonato, Luis Gustavo</creator><creator>Barr, Brian</creator><creator>Silva, Claudio T</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20200721</creationdate><title>Melody: Generating and Visualizing Machine Learning Model Summary to Understand Data and Classifiers Together</title><author>Chan, Gromit Yeuk-Yin ; Bertini, Enrico ; Nonato, Luis Gustavo ; Barr, Brian ; Silva, Claudio T</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-60642e31e5a97b23abd3b6a2cc00cc042d70061efc80f17dcbf670eeac3262e33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Human-Computer Interaction</topic><toplevel>online_resources</toplevel><creatorcontrib>Chan, Gromit Yeuk-Yin</creatorcontrib><creatorcontrib>Bertini, Enrico</creatorcontrib><creatorcontrib>Nonato, Luis Gustavo</creatorcontrib><creatorcontrib>Barr, Brian</creatorcontrib><creatorcontrib>Silva, Claudio T</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chan, Gromit Yeuk-Yin</au><au>Bertini, Enrico</au><au>Nonato, Luis Gustavo</au><au>Barr, Brian</au><au>Silva, Claudio T</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Melody: Generating and Visualizing Machine Learning Model Summary to Understand Data and Classifiers Together</atitle><date>2020-07-21</date><risdate>2020</risdate><abstract>With the increasing sophistication of machine learning models, there are growing trends of developing model explanation techniques that focus on only one instance (local explanation) to ensure faithfulness to the original model. While these techniques provide accurate model interpretability on various data primitive (e.g., tabular, image, or text), a holistic Explainable Artificial Intelligence (XAI) experience also requires a global explanation of the model and dataset to enable sensemaking in different granularity. Thus, there is a vast potential in synergizing the model explanation and visual analytics approaches. In this paper, we present MELODY, an interactive algorithm to construct an optimal global overview of the model and data behavior by summarizing the local explanations using information theory. The result (i.e., an explanation summary) does not require additional learning models, restrictions of data primitives, or the knowledge of machine learning from the users. We also design MELODY UI, an interactive visual analytics system to demonstrate how the explanation summary connects the dots in various XAI tasks from a global overview to local inspections. We present three usage scenarios regarding tabular, image, and text classifications to illustrate how to generalize model interpretability of different data. Our experiments show that our approaches: (1) provides a better explanation summary compared to a straightforward information-theoretic summarization and (2) achieves a significant speedup in the end-to-end data modeling pipeline.</abstract><doi>10.48550/arxiv.2007.10614</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2007.10614
ispartof
issn
language eng
recordid cdi_arxiv_primary_2007_10614
source arXiv.org
subjects Computer Science - Human-Computer Interaction
title Melody: Generating and Visualizing Machine Learning Model Summary to Understand Data and Classifiers Together
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T15%3A45%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Melody:%20Generating%20and%20Visualizing%20Machine%20Learning%20Model%20Summary%20to%20Understand%20Data%20and%20Classifiers%20Together&rft.au=Chan,%20Gromit%20Yeuk-Yin&rft.date=2020-07-21&rft_id=info:doi/10.48550/arxiv.2007.10614&rft_dat=%3Carxiv_GOX%3E2007_10614%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true