[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82091-en":3,"doc-seo-82091-105":29,"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":13,"seo_description":14,"update_tm":27,"read_time":28},82091,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Pattern-Aware Graph Neural Networks for Handling Missing Data","Missing data is common in real-world datasets, and conventional approaches either drop incomplete samples or impute values while assuming missingness is random. Missingness patterns themselves may carry predictive signal, especially in settings like medical testing. This work proposes pattern-aware graph neural networks that encode which features are missing alongside observed values. Experiments on seven UCI datasets show average gains of 17% balanced accuracy and 22% macro F1, with strong dataset-dependent effects and competitive performance from simple random pattern embeddings.","Pattern-Aware Graph Neural Networks for Handling  \nMissing Data  \nMinett Tran, Taehee Jeong  \nSan Jose State University  \nminett.tran, [taehee.jeong @sjsu.edu](taehee.jeong @sjsu.edu)  \narXiv :2607 .089 15v 1 [ cs .LG] 9 Jul 2026  \nAbstract—Missing data is ubiquitous in real-world datasets. Traditional methods either discard incomplete samples or apply imputation techniques that ignore potentially informative missingness patterns, implicitly assuming that missingness occurs randomly. However, missingness patterns might provide additional information. We propose pattern-aware graph neural networks that explicitly encode which features are missing alongside observed values. We used four encoding strategies—learned embeddings, frozen random embeddings, statistical features, and hierarchical representations—across seven UCI datasets with naturally occurring missingness. Our Pattern-aware methods achieve substantial improvements over baselines, with an average improvement of 17% in balanced accuracy and 22% in F1-macro across all datasets. The benefits vary significantly by dataset: annealing shows dramatic improvement (+80% balanced accuracy), while hepatitis and soybean show minimal gains (+4– 5%). Notably, even simple random pattern embeddings perform comparably to learned embeddings (0.650 vs 0.663 balanced accuracy), suggesting that distinguishing between patterns maybe more important than task-specific optimization. Our ablation study reveals that attention mechanisms, while helpful, are not critical when pattern information is available—simple mean aggregation with pattern awareness achieves 0.640 balanced accuracy compared to 0.645 for attention-based variants. Our code and data are available at [https://github.com/TranMinett/](https://github.com/TranMinett/)[ ](https://github.com/TranMinett/)pattern aware GRAPE.  \nIndex Terms—Graph Neural Networks, Missing Data, Tabular Data, Pattern Encoding, Bipartite Graphs  \nI. INTRODUCTION  \nMissing data pervades real-world datasets: medical records often contain missing diagnostic tests, survey respondents frequently skip questions, and sensors periodically fail. The traditional approach handles such incompleteness either by deleting samples with missing values or by imputing them using methods such as mean substitution or k-nearest neighbors. However, these approaches rest on a critical assumption—that missingness occurs randomly.  \nConsider a clinical setting where physicians order extensive diagnostic tests only for patients presenting severe symptoms. In this scenario, which tests are missing reveals information about disease severity independent of the test results themselves. Traditional imputation methods ignore this signal,  \nThis work was supported in part by a Mobilint Grant awarded to San Jose State University. (Corresponding author: Taehee Jeong)  \n2026 International Conference on Advances in Artificial Intelligence and Machine Learning (AAIML), 20-22 March 2026, IEEE Copyright 2026  \nfocusing solely on estimating the unobserved values rather than leveraging the informative structure of missingness.  \nGraph Neural Networks (GNNs) offer an alternative paradigm for handling incomplete data. GRAPE [1] represents each sample data as a bipartite graph where feature nodes connect only to observed values, naturally accommodating arbitrary missingness patterns without imputation. However, GRAPE treats all missingness patterns identically: two patients with different patterns of missing tests receive equivalent graph structures provided they share the same values for observed features, discarding potentially valuable information about which measurements were deemed necessary.  \nThis raises a fundamental question: does explicitly encoding missingness patterns improve predictive performance? And critically, under what conditions does this added complexity justify itself? These questions carry practical significance beyond academic interest, as pattern-aware methods introduce archite","cbCaijAw0QKaBIrW","https://ap.wps.com/l/cbCaijAw0QKaBIrW","pdf",736504,1,7,"English","en",105,"# Introduction\n## Missing Data Mechanisms\n## Graph Neural Networks for Incomplete Data\n# Pattern-Aware GRAPE\n## Encoding Missingness Patterns\n## Experimental Results","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses how to handle missing data in real-world datasets where missingness patterns may contain informative signal rather than occurring at random.\"},{\"question\":\"How do the proposed models incorporate missingness information?\",\"answer\":\"The method extends GRAPE by encoding missingness patterns into pattern embeddings and combining them with representations of observed features before message passing.\"},{\"question\":\"What performance improvements are reported?\",\"answer\":\"Across seven UCI datasets, pattern-aware methods improve balanced accuracy by an average of 17% and macro F1 by 22%, with some datasets showing large gains and others only minimal improvements.\"}]",1784178173,18,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"pattern-aware-graph-neural-networks-for-handling-missing-data","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/pattern-aware-graph-neural-networks-for-handling-missing-data/82091/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",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 paper address?","Question",{"text":75,"@type":76},"The paper addresses how to handle missing data in real-world datasets where missingness patterns may contain informative signal rather than occurring at random.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the proposed models incorporate missingness information?",{"text":80,"@type":76},"The method extends GRAPE by encoding missingness patterns into pattern embeddings and combining them with representations of observed features before message passing.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance improvements are reported?",{"text":84,"@type":76},"Across seven UCI datasets, pattern-aware methods improve balanced accuracy by an average of 17% and macro F1 by 22%, with some datasets showing large gains and others only minimal improvements.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]