[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126962-en":3,"doc-seo-126962-105":30,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},126962,687207024478,"Liam","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Empowering Causal Machine Learning for Large-Scale Manufacturing Pipelines with Knowledge Graphs","Understanding causal relations within manufacturing pipelines is essential for anomaly detection and root cause analysis, yet existing causal machine learning (causal ML) struggles to scale across the very large variable spaces found in real production. This work proposes integrating expert domain knowledge by representing manufacturing processes as knowledge graphs (KGs). KGs capture context on interactions and dependencies across pipeline stages, constraining causal discovery search and improving computational tractability, learning stability, and causal learning accuracy in large-scale manufacturing settings.","University of South Carolina  \nScholar Commons  \n\n| Faculty Publications | Computer Science and Engineering, Department of |\n| --- | --- |\n| 2024\u003Cbr>Empowering Causal Machine Learning for Large-Scale\u003Cbr>Manufacturing Pipelines with Knowledge Graphs Yuxin Zi\u003Cbr>Cory Henson\u003Cbr>Amit P. Sheth\u003Cbr>University of South Carolina-Columbia, [amit@sc.edu](amit@sc.edu)\u003Cbr>Follow this and additional works at: [https://scholarcommons.sc.edu/csce_facpub](https://scholarcommons.sc.edu/csce_facpub)\u003Cbr> Part of the Computer Sciences Commons, and the Engineering Commons |  |\n\nPublication Info  \nPreprint version 2024.  \nThis Article is brought to you by the Computer Science and Engineering, Department of at Scholar Commons. It has been accepted for inclusion in Faculty Publications by an authorized administrator of Scholar Commons. For more information, please [contact](contact digres@mailbox.sc.edu)[ digres@mailbox.sc.edu](contact digres@mailbox.sc.edu).  \nEmpowering Causal Machine Learning for Large-scale Manufacturing Pipelines with Knowledge Graphs  \nYuxin Zi1,∗,†, Cory Henson2 and Amit Sheth1  \n1 Artificial Intelligence Institute, University of South Carolina, Columbia, USA 2 Bosch Center for Artificial Intelligence, Pittsburgh, USA  \nAbstract  \nUnderstanding causal relations within manufacturing pipelines is crucial for key manufacturing tasks such as anomaly detection and root cause analysis. However, existing causal machine learning (causal ML) approaches struggle to scale effectively to the vast number of variables present in manufacturing settings. We advocate for incorporating domain knowledge within the manufacturing pipelines, represented as knowledge graphs (KGs), for designing causal ML methods for large-scale manufacturing problems. Knowledge graphs can encode rich contextual information about the interactions and dependencies between different components and stages of the manufacturing pipeline, providing a structured framework to guide the discovery of causal relationships. By incorporating KGs, causal ML models can leverage both data-driven approaches and domain knowledge, enhancing scalability and improving the accuracy of causal learning in large scale manufacturing settings.  \n1. Introduction  \nCausal machine learning (causal ML) encompasses ML methods aimed at identifying cause-and-effect relationships among variables, primarily using observational data. Manufacturing pipelines involve tens of thousands of observed and unobserved variables, including physical sensor readings, material properties, machine parameters, and environmental factors. Understanding the causal relations between these variables is critical for downstream tasks such as anomaly detection, root cause analysis and process optimization [1] . Existing causal ML methods have demonstrated effectiveness with relatively small numbers of variables; however, they either cannot scale to manufacturing problem or do so with significant inefficiency. The challenge with scaling arises from the combinatorial complexity of evaluating possible causal relationships among variables [2], compounded by noise, confounders, and unobserved variables. We argue that integrating expert-curated knowledge graphs (KGs) of manufacturing processes can enable the development of scalable approaches that discern meaningful causal relationships amidst the complexity of data. Specifically, this knowledge can clarify existing causal relationships and specify additional constraints over the search space, drastically improving the computational tractability and learning stability of causal ML methods. Due to their symbolic form, KGs can significantly enhance the interpretability of causal ML model outputs. Such knowledgeguided approaches have the potential to enhance both the scalability and accuracy of causal ML techniques, ultimately supporting more informed decision-making and process optimization in realworld manufacturing environments.  \n2. Constructing KGs for Manufacturing Pipelines  \nTh","cbCaikvPd1qhSboc","https://ap.wps.com/l/cbCaikvPd1qhSboc","pdf",110860,1,4,"English","en",105,"# Introduction\n## Challenges in scaling causal ML for manufacturing\n# Constructing KGs for Manufacturing Pipelines\n## Organizing expert knowledge into knowledge graphs\n## Information types integrated into KGs\n# KGs Enables Large-Scale Causal ML for Manufacturing","[{\"question\":\"Why is causal machine learning important in manufacturing pipelines?\",\"answer\":\"Causal ML helps identify cause-and-effect relationships among variables, supporting downstream tasks like anomaly detection and root cause analysis, as well as process optimization.\"},{\"question\":\"What scaling challenge limits existing causal ML approaches for manufacturing?\",\"answer\":\"Manufacturing pipelines involve tens of thousands of variables, and the combinatorial complexity of evaluating candidate causal relationships—amplified by noise, confounders, and latent variables—makes scaling difficult.\"},{\"question\":\"How do knowledge graphs improve large-scale causal learning?\",\"answer\":\"Knowledge graphs encode contextual dependencies and interactions across pipeline stages, constrain the causal discovery search space, and improve computational tractability and learning stability while enhancing interpretability.\"}]","Empowering Causal Machine Learning for Large-Scale Manufacturing Pipelines with Knowledge Graphs | PDF",1785935925,10,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"empowering-causal-machine-learning-for-large-scale-manufacturing-pipelines-with-knowledge-graphs","",{"@graph":36,"@context":84},[37,53,67],{"@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":21},"https://docshare.wps.com/document/empowering-causal-machine-learning-for-large-scale-manufacturing-pipelines-with-knowledge-graphs/126962/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is causal machine learning important in manufacturing pipelines?","Question",{"text":74,"@type":75},"Causal ML helps identify cause-and-effect relationships among variables, supporting downstream tasks like anomaly detection and root cause analysis, as well as process optimization.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What scaling challenge limits existing causal ML approaches for manufacturing?",{"text":79,"@type":75},"Manufacturing pipelines involve tens of thousands of variables, and the combinatorial complexity of evaluating candidate causal relationships—amplified by noise, confounders, and latent variables—makes scaling difficult.",{"name":81,"@type":72,"acceptedAnswer":82},"How do knowledge graphs improve large-scale causal learning?",{"text":83,"@type":75},"Knowledge graphs encode contextual dependencies and interactions across pipeline stages, constrain the causal discovery search space, and improve computational tractability and learning stability while enhancing interpretability.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]