[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83284-en":3,"doc-seo-83284-105":30,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83284,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation","Deep learning time-series imputation often depends on localized temporal context in the corrupted input, which underperforms when data are non-stationary, weakly correlated, or contain infrequent patterns that cannot be reliably reconstructed from nearby observations alone. This work introduces ALER-TI, a retrieval-augmented framework that leverages historical patterns to補 strengthen missing-value reconstruction. Latent Embedding Alignment (LEA) reduces representation mismatch by masking in latent space, enabling cached candidates. A model-agnostic module improves multiple strong baselines and robustness across six real-world datasets under varying missing rates.","ALER-TI: Aligned Latent Embedding Retrieval for  \nTime Series Imputation  \nXuan-Thong Truong 1 , Trung-Kien Le 1 , Tung Kieu2 , Thi-Thu Nguyen 1 , Nhat-Hai Nguyen 1,*  \n1 School of Computer Science, Hanoi University of Science and Technology, Hanoi, Vietnam  \n2 Department of Computer Science, Aalborg University, Aalborg, Denmark  \n* Corresponding author: [hai.nguyennhat@hust.edu.vn](hai.nguyennhat@hust.edu.vn)  \narXiv :2607 .07640v 1 [ cs .LG] 8 Jul 2026  \nAbstract—Deep learning has significantly advanced time series imputation, yet most existing architectures primarily rely on localized temporal context within the corrupted input sequence. This reliance can be limiting in real-world scenarios, where time series often exhibit non-stationary dynamics, weak temporal correlations, and infrequent patterns that are difficult to reconstruct from nearby observations alone. In this paper, we propose ALER-TI, Aligned Latent Embedding Retrieval for Time Series Imputation, a retrieval-augmented framework that explicitly leverages historical patterns to supplement degraded local context for more reliable missing-value reconstruction. The core of ALER-TI is Latent Embedding Alignment (LEA), which mitigates the representation mismatch between corrupted queries and complete historical candidates. By applying post-hoc masking in the latent space, LEA aligns candidates with the query’s missingness pattern while allowing historical embeddings to be pre-computed and cached for efficient retrieval. ALER-TI is model-agnostic and can be integrated with various imputation backbones through a lightweight adaptation module. Extensive experiments on six real-world datasets under different missing rates demonstrate that ALER-TI consistently improves strong baseline models and enhances robustness across diverse imputation settings.  \nIndex Terms—Time series imputation, retrieval-augmented learning, model-agnostic framework, contrastive learning.  \nI. INTRODUCTION  \nTime series data collected from real-world sensors and monitoring systems are frequently affected by missing values due to sensor malfunctions, transmission failures, or human errors [11] . Since many downstream analytical models require complete data matrices as inputs, missing observations can severely undermine the reliability of critical applications, ranging from healthcare monitoring [5], [19] and financial forecasting [1] to industrial anomaly detection [4] . To address this challenge, various deep learning architectures have been developed for time series imputation, including CNN-based models [18], [22], Transformer variants [8], [17], and decomposition-based networks [23], [26] . Despite their different architectural designs, these methods mainly rely on the localized temporal context within the corrupted input sequence to reconstruct missing observations.  \nHowever, real-world time series often exhibit complex and non-stationary dynamics driven by non-deterministic processes, where temporal correlations may weaken over time [17], [24] . Such dynamics can lead to infrequent patterns and distributional variations, making it difficult for models to infer missing values from the observed local context alone. This limitation is  \n|  Re-compute |  Pre-compute |\n| --- | --- |\n\nFig. 1: Comparison of retrieval strategies for time-series imputation. (a) Asymmetric Retrieval (AR): Encodes the query and candidates independently, with candidates represented as fully observed trajectories. (b) On-the-fly Masking (OM): Applies masking before encoding to align candidate representations with the query pattern, but requires online re-encoding at inference time. (c) LEA (Ours): Uses mask-agnostic encoding and performs masking in latent space, enabling reuse of pre-computed embeddings while preserving query-aware alignment.  \nespecially problematic when the corrupted segment corresponds to a rare event or when nearby observations provide insufficient correlated information for reliable reconstruction. ","cbCairslxtiyDfSU","https://ap.wps.com/l/cbCairslxtiyDfSU","pdf",602138,5,1,10,"English","en",105,"# Introduction\n## Problem of missing values in time series\n## Limitations of localized-context imputation\n## Retrieval-augmented imputation and key challenge\n## Naive asymmetric retrieval and representation mismatch","[{\"question\":\"What limitation do existing deep learning time-series imputation methods face?\",\"answer\":\"They mainly rely on localized temporal context in the corrupted sequence, which can fail under non-stationary dynamics, weak temporal correlations, and rare/infrequent patterns.\"},{\"question\":\"How does ALER-TI address the representation mismatch introduced by missingness?\",\"answer\":\"ALER-TI uses Latent Embedding Alignment (LEA), applying post-hoc masking in the latent space so candidate embeddings align with the query’s missingness pattern despite cached historical candidates.\"},{\"question\":\"Why is retrieval for imputation different from retrieval for forecasting?\",\"answer\":\"In forecasting the query is typically fully observed, enabling similarity estimation from complete context, while imputation queries are corrupted, making similarity measurement between corrupted queries and clean candidates more challenging.\"}]",1784186491,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"aler-ti-aligned-latent-embedding-retrieval-for-time-series-imputation","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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/aler-ti-aligned-latent-embedding-retrieval-for-time-series-imputation/83284/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What limitation do existing deep learning time-series imputation methods face?","Question",{"text":76,"@type":77},"They mainly rely on localized temporal context in the corrupted sequence, which can fail under non-stationary dynamics, weak temporal correlations, and rare/infrequent patterns.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does ALER-TI address the representation mismatch introduced by missingness?",{"text":81,"@type":77},"ALER-TI uses Latent Embedding Alignment (LEA), applying post-hoc masking in the latent space so candidate embeddings align with the query’s missingness pattern despite cached historical candidates.",{"name":83,"@type":74,"acceptedAnswer":84},"Why is retrieval for imputation different from retrieval for forecasting?",{"text":85,"@type":77},"In forecasting the query is typically fully observed, enabling similarity estimation from complete context, while imputation queries are corrupted, making similarity measurement between corrupted queries and clean candidates more challenging.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"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":22,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":22,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":20,"slug":137},19,"General","general"]