[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290740-105":59,"doc-detail-290740-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","proactively-screening-machine-learning-pipelines-with-arguseyes","Proactively Screening Machine Learning Pipelines with ArgusEyes","","Machine learning (ML) software is widespread, yet ML pipelines frequently encounter data-related failures such as data leakage, label errors, and fairness violations. These problems are often discovered only after deployment, when harm has already occurred in production, demanding urgent and ad-hoc debugging. ArgusEyes is presented as a system for continuous integration that instruments, executes, and screens ML pipelines for declaratively specified pipeline issues by analyzing data artifacts and provenance. Three scenarios are demonstrated: mislabeled images, price-prediction leakage, and fairness issues in credit scoring.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/proactively-screening-machine-learning-pipelines-with-arguseyes/290740/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/proactively-screening-machine-learning-pipelines-with-arguseyes/290740.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-02","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What kinds of data-related issues does ArgusEyes target in ML pipelines?","Question",{"text":113,"@type":114},"It targets issues such as data leakage from train to test, label errors in training samples, and fairness violations that lead to biased predictions.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does ArgusEyes help detect problems earlier than after deployment?",{"text":118,"@type":114},"ArgusEyes instruments, executes, and screens ML pipelines during continuous integration, analyzing data artifacts and provenance to catch potential problems before production deployment.",{"name":120,"@type":111,"acceptedAnswer":121},"What demonstration scenarios are used to validate the system?",{"text":122,"@type":114},"The system is demonstrated for mislabeled images in a computer vision pipeline, data leakage in a price prediction pipeline, and fairness violations in a credit scoring pipeline.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290740,1789642482,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":24,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":144,"preview_page_count":4},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","UvA-DARE (Digital Academic Repository)  \nProactively Screening Machine Learning Pipelines with ArgusEyes  \nSchelter, S. ; Grafberger, S. ; Guha, S. ; Karlaš, B. ; Zhang, C.  \nDOI  \n10.1145/3555041.3589682  \nPublication date  \n2023  \nDocument Version  \nFinal published version  \nPublished in  \nSIGMOD '23 Companion  \nLicense  \nCC BY-SA  \nLink to publication  \nCitation for published version (APA):  \nSchelter, S. , Grafberger, S. , Guha, S. , Karlaš, B. , & Zhang, C. (2023) . Proactively Screening Machine Learning Pipelines with ArgusEyes. In SIGMOD '23 Companion: Companion of the 2023 ACM/SIGMOD International Conference on Management of Data : June 18-23, 2023, Seattle, WA, USA (pp. 91–94) . Association for Computing Machinery.  \n[https://doi.org/10.1145/3555041.3589682](https://doi.org/10.1145/3555041.3589682)  \nGeneral rights  \nIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons) .  \nDisclaimer/Complaints regulations  \nIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: [https://uba.uva.nl/en/contact](https://uba.uva.nl/en/contact), or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.  \nUvA-DARE is a service provided by the library of the University of Amsterdam ( [http](https://dare. uva. nl)[s](https://dare. uva. nl)[://dare. uva. nl](https://dare. uva. nl))  \nDownload date:28 Nov 2023  \nProactively Screening Machine Learning Pipelines  \nwith ArgusEyes  \nSebastian Schelter  \nUniversity of Amsterdam Amsterdam, The Netherlands [s.schelter@uva.nl](s.schelter@uva.nl)  \nStefan Grafberger  \nAIRLab, University of Amsterdam Amsterdam, The Netherlands [s.grafberger@uva.nl](s.grafberger@uva.nl)  \nShubha Guha  \nAIRLab, University of Amsterdam Amsterdam, The Netherlands [s.grafberger@uva.nl](s.grafberger@uva.nl)  \nBojan Karlaš  \nHarvard University Boston, United States [bojan_karlas@hms.harvard.edu](bojan_karlas@hms.harvard.edu)  \nCe Zhang  \nETH Zürich Zürich, Switzerland [ce.zhang@inf.ethz.ch](ce.zhang@inf.ethz.ch)  \nABSTRACT  \nSoftware systems that learn from data with machine learning (ML) are ubiquitous. ML pipelines in these applications often suffer from a variety of data-related issues, such as data leakage, label errors or fairness violations, which require reasoning about complex dependencies between their inputs and outputs. These issues are usually only detected in hindsight after deployment, after they caused harm in production. We demonstrate ArgusEyes, a system which enables data scientists to proactively screen their ML pipelines for data-related issues as part of continuous integration. ArgusEyes instruments, executes and screens ML pipelines for declaratively specified pipeline issues, and analyzes data artifacts and their provenance to catch potential problems early before deployment to production. We demonstrate our system for three scenarios: detecting mislabeled images in a computer vision pipeline, spotting data leakage in a price prediction pipeline, and addressing fairness violations in a credit scoring pipeline.  \nCCS CONCEPTS  \n• Information systems → Data management systems;  \nKEYWORDS  \nMachine learning pipelines, provenance tracking, data validation  \nACM Reference Format:  \nSebastian Schelter, Stefan Grafberger, Shubha Guha, Bojan Karlaš, Ce Zhang.  \n2023. Proactively Screening Machine Learning Pipelines with ArgusEyes. In Companion of the 2023 International Conference on Management of Data (SIGMOD-Companion ’23), June 18–23, 2023, Seattle, WA,","cbCaibGrHUY22wZa","https://ap.wps.com/l/cbCaibGrHUY22wZa","pdf",2432991,"English","# Abstract\n# 1 Introduction\n## Data-related issues in ML pipelines\n## Proactive pipeline screening with ArgusEyes","[{\"question\":\"What kinds of data-related issues does ArgusEyes target in ML pipelines?\",\"answer\":\"It targets issues such as data leakage from train to test, label errors in training samples, and fairness violations that lead to biased predictions.\"},{\"question\":\"How does ArgusEyes help detect problems earlier than after deployment?\",\"answer\":\"ArgusEyes instruments, executes, and screens ML pipelines during continuous integration, analyzing data artifacts and provenance to catch potential problems before production deployment.\"},{\"question\":\"What demonstration scenarios are used to validate the system?\",\"answer\":\"The system is demonstrated for mislabeled images in a computer vision pipeline, data leakage in a price prediction pipeline, and fairness violations in a credit scoring pipeline.\"}]","Proactively Screening Machine Learning Pipelines with ArgusEyes | PDF",13]