[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121088-en":3,"doc-seo-121088-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121088,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Visualization for Trust in Machine Learning Revisited - The State of the Field in 2023","Visualization for explainable and trustworthy machine learning continues to be a core topic in information visualization and visual analytics across domains including medicine, finance, and bioinformatics. Building on a 2020 state-of-the-art report of 200 techniques, a peer-reviewed collection was updated and analyzed to provide 542 techniques in an online survey browser. Findings based on fall 2023 data indicate rapid growth in trust-oriented visualization, supporting improved explainability methods and validation of newer deep learning architectures, alongside eight open challenges for visualization in ML.","© 2024 IEEE. This is the author’s version of the article that has been published in IEEE Computer Graphics and Applications. The final version of this record is available at: 10. 1109/MCG.2024.3360881  \nFEATURE ARTICLE  \nVisualization for Trust in Machine Learning Revisited: The State of the Field in 2023  \nAngelos Chatzimparmpas, Northwestern University, Evanston, IL, 60208, USA Kostiantyn Kucher, Linköping University, Norrköping, 60233, Sweden  \nAndreas Kerren, Linköping University, Norrköping, 60233, Sweden; Linnaeus University, Växjö, 35195, Sweden  \narXiv :2403 . 12005v2 [ cs .HC] 18 Apr 2024  \nAbstract—Visualization for explainable and trustworthy machine learning remains one of the most important and heavily researched fields within information visualization and visual analytics with various application domains, such as medicine, finance, and bioinformatics. After our 2020 state-of-the-art report comprising 200 techniques, we have persistently collected peer-reviewed articles describing visualization techniques, categorized them based on the previously established categorization schema consisting of 119 categories, and provided the resulting collection of 542 techniques in an online survey browser. In this survey article, we present the updated findings of new analyses of this dataset as of fall 2023 and discuss trends, insights, and eight open challenges for using visualizations in machine learning. Our results corroborate the rapidly growing trend of visualization techniques for increasing trust in machine learning models in the past three years, with visualization found to help improve popular model explainability methods and check new deep learning architectures, for instance.  \nT  \nrust in machine learning (ML) models is a major concern in leveraging these technologies for real-world applications.1 Yet, ML models are  \nbeing deployed in different application fields, and their role in decision-making processes is growing rapidly. Fields such as healthcare and criminal justice increasingly depend on ML models to make irreversible decisions that impact human lives.2 However, the blackbox nature of some ML models poses a threat to their adoption. Domain experts often hesitate to rely on ML models for high-risk decision-making, as the inability  \nto understand their inner workings fosters mistrust.3  \nIn response to the outlined challenges, researchers in academia and industry have designed several innovative solutions. For example, Google’s Explainable Artificial Intelligence (AI) Cloud and Descriptive mAchine Learning EXplanations (DALEX) package aims to improve the collaboration among domain experts to address the challenges posed by the complexity of AI. Except for all the visualization techniques analyzed in this survey article, recent frameworks set a founda-  \nXXXX-XXX © 2023 IEEE  \nDigital Object Identifier 10.1109/XXX.0000.0000000  \ntion for developing techniques that facilitate users in communicating and externalizing their trust explicitly across varied ML stages and in understanding the complexities of human and AI interactions.4,5 Other works bridge the significant gap between ML outputsand human cognition by promoting a cross-disciplinary approach and building a robust model designed to examine the sender’s explanation intention and its ensuing impact on the receiver’s perception.6,7  \nWe base this work upon the findings of our previously published survey articles8,9 and others that have stressed the need for visual analytics (VA) to improve trust and transparency in areas such as dimensionality reduction (DR),11 deep learning (DL),12,13 and ML in general. 14,15 After our 2020 state-of-the-art report (STAR) comprising 200 techniques,9 we have been collecting peer-reviewed articles describing visualization techniques for enhancing trust in ML, categorizing them based on the previously established categorization schema of 18 groups and 119 categories in total, and providing the hand-curated compilation of 54","cbCaiinZPvh3pNHe","https://ap.wps.com/l/cbCaiinZPvh3pNHe","pdf",8048731,1,14,"English","en",105,"# Introduction\n## Trust as a real-world adoption barrier\n## Black-box nature and mistrust in high-risk domains\n# Background and Related Work\n## Prior 2020 state-of-the-art (STAR) and data collection\n## Literature search and trust definition\n# Method and Contributions\n## Updated dataset analysis for fall 2023\n## Trust levels and categorization of 542 techniques\n## New analyses: topic, temporal, correlation, pattern mining\n## Interactive survey browser for stakeholders\n# Results and Open Challenges\n## Observed trends in trust visualization growth\n## Insights and eight open challenges","[{\"question\":\"What problem does the document address regarding machine learning trust?\",\"answer\":\"It addresses mistrust caused by uncertainty and the black-box nature of some machine learning models, which can hinder adoption in real-world, high-risk decision-making domains.\"},{\"question\":\"How was the visualization technique dataset updated for this 2023 review?\",\"answer\":\"The authors continuously collected peer-reviewed articles describing trust-related visualization techniques, categorized them using an existing schema, and produced a curated compilation of 542 techniques for an online survey browser.\"},{\"question\":\"What key contributions does the survey article claim for the fall 2023 state of the field?\",\"answer\":\"It provides techniques categorized by trust levels and reports trends from new analyses, offers an interactive survey browser for exploring the literature, and identifies eight open challenges for improving the trustworthiness of the ML process.\"}]","Visualization for Trust in Machine Learning Revisited - The State of the Field in 2023 | PDF",1785733659,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"visualization-for-trust-in-machine-learning-revisited-the-state-of-the-field-in-2023","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/visualization-for-trust-in-machine-learning-revisited-the-state-of-the-field-in-2023/121088/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the document address regarding machine learning trust?","Question",{"text":75,"@type":76},"It addresses mistrust caused by uncertainty and the black-box nature of some machine learning models, which can hinder adoption in real-world, high-risk decision-making domains.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How was the visualization technique dataset updated for this 2023 review?",{"text":80,"@type":76},"The authors continuously collected peer-reviewed articles describing trust-related visualization techniques, categorized them using an existing schema, and produced a curated compilation of 542 techniques for an online survey browser.",{"name":82,"@type":73,"acceptedAnswer":83},"What key contributions does the survey article claim for the fall 2023 state of the field?",{"text":84,"@type":76},"It provides techniques categorized by trust levels and reports trends from new analyses, offers an interactive survey browser for exploring the literature, and identifies eight open challenges for improving the trustworthiness of the ML process.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]