[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85089-en":3,"doc-seo-85089-105":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":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},85089,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Drift Aware Temporal Graph Rewiring (DATGR) for Adaptive Semantic Modeling in Biomedical Text","Drift-Aware Temporal Graph Rewiring (DATGR) addresses semantic drift in biomedical text by updating a temporal word co-occurrence graph at the edge level without full re-embedding. Static models fail to reflect emerging term associations, harming downstream retrieval accuracy. DATGR performs temporal segmentation, estimates local drift from sentence embeddings, applies a drift-weighted logistic rewiring rule to update edge strengths, and evaluates link prediction over BIOMRC time windows. Results show AUROC gains (~0.066) with stable precision-recall behavior.","Drift-Aware Temporal Graph Rewiring (DATGR) for Adaptive Semantic Modeling in Biomedical Text  \nBharathwaj Vijayakumar1 and Sahana K. Varadaraju2  \nStatic models therefore misrepresent emerging associationsand reduce retrieval accuracy when used for downstream analysis.  \nTo mitigate this, several temporal embedding frameworks [6],[7] and dynamic graph neural networks (DGNNs), and surveys thereof [8], [10], have been proposed. While effective, many methods require retraining or sequential finetuning for each time slice; these approaches incur significant computational cost and limiting interpretability. Furthermore, most focus on node-level drift, how individual term vectors change, rather than on edge-level drift, which captures the evolving co-occurrence structure among terms. Instead of retraining embeddings, DATGR rewires the word-cooccurrence graph using a drift-weighted logistic update rule, enabling continuous adaptation without full re-embedding. Evaluated on the BIOMRC corpus, the proposed model achieved an absolute AUROC improvement of approximately 0.066 (0 .699 vs. 0.633) over a static baseline, while maintaining comparable AUPRC performance (0 .738 vs. 0.744) . These results demonstrate that lightweight, feedback-driven edge updates can effectively capture semantic evolution while preserving precision.  \nThe key contributions of this work are as follows:  \n• A drift-aware rewiring mechanism for temporal cooccurrence graphs that models edge evolution efficiently without retraining embeddings (DATGR);  \n• An empirical demonstration on real biomedical text, showing improved link-prediction AUROC and stable precision-recall behavior across temporal windows;  \n• A scalable foundation for adaptive semantic modeling applicable to evolving domains such as biomedical knowledge tracking, retrieval augmentation, and ontology maintenance.  \nII. RELATED WORK  \nResearch on modeling temporal change in language has evolved along three major directions: static co-occurrence graphs, temporal word embeddings, and dynamic graph learning.  \nEarly approaches based on word co-occurrence statistics treated term relations as static [1] . While such representations capture word associations effectively at a single point in time, they ignore how meaning shifts as domains evolve. Distributional embeddings such as word2vec [2] and GloVe [3] improved semantic representation but remained time-invariant. Recent work on temporal embeddings for biomedical literature has explored how contextual meaning changes across time [11] . To address temporal variability,  \nresearchers proposed diachronic or dynamic embeddings that explicitly model meaning change across time. Hamilton et al. [4] analyzed word embedding trajectories to uncover statistical laws of semantic change, while Tahmasebi et al. [5] surveyed computational methods for detecting lexical semantic change. Bamler and Mandt [6] introduced probabilistic dynamic embeddings, modeling word transitions as latent trajectories through time. Nicholson et al. [7] analyzed large-scale biomedical corpora and demonstrated domainspecific semantic drift in biomedical scientific language.  \nDynamic graph learning addresses temporal networks directly. Recent surveys of DGNNs and temporal knowledge graphs (e.g., [8]) summarize architectures that update node representations as edges arrive [8] . However, many such methods emphasize node embeddings rather than direct edge updates reflecting co-occurrence strength. The proposed DATGR differs by explicitly modeling edge drift via a lightweight logistic rewiring rule, achieving temporal sensitivity while remaining interpretable and efficient.  \nIII. METHODOLOGY  \nThe proposed DATGR framework models the evolution of biomedical semantics through incremental, edge-level graph adaptation rather than full re-embedding. It comprises four modules: (1) temporal segmentation of the corpus, (2) drift estimation using sentence embeddings, (3) drift-weighted graph rewiring, a","cbCaimRcgc49aTu3","https://ap.wps.com/l/cbCaimRcgc49aTu3","pdf",529095,3,1,6,"English","en",105,"# Related Work\n# Methodology\n## Temporal Segmentation and Graph Construction\n## Drift-Aware Rewiring Rule","[{\"question\":\"Why do static semantic models underperform on biomedical text over time?\",\"answer\":\"Static representations treat term relationships as time-invariant, missing how meanings and associations shift as biomedical domains evolve. This leads to reduced retrieval accuracy and misrepresentation of emerging links.\"},{\"question\":\"How does DATGR adapt semantics without retraining embeddings?\",\"answer\":\"DATGR keeps embeddings static and instead rewires a word co-occurrence graph incrementally. A drift-aware logistic update rule adjusts edge weights using prior edge strength, current co-occurrence, and local drift signals.\"},{\"question\":\"What is the role of temporal segmentation in DATGR?\",\"answer\":\"The corpus is split into chronological windows, and for each window a weighted graph is constructed from tokenized abstracts. This enables computing normalized edge strengths and tracking their changes across successive time slices.\"}]",1784201026,15,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"drift-aware-temporal-graph-rewiring-datgr-for-adaptive-semantic-modeling-in-biomedical-text","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/drift-aware-temporal-graph-rewiring-datgr-for-adaptive-semantic-modeling-in-biomedical-text/85089/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","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},"Why do static semantic models underperform on biomedical text over time?","Question",{"text":75,"@type":76},"Static representations treat term relationships as time-invariant, missing how meanings and associations shift as biomedical domains evolve. This leads to reduced retrieval accuracy and misrepresentation of emerging links.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does DATGR adapt semantics without retraining embeddings?",{"text":80,"@type":76},"DATGR keeps embeddings static and instead rewires a word co-occurrence graph incrementally. A drift-aware logistic update rule adjusts edge weights using prior edge strength, current co-occurrence, and local drift signals.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of temporal segmentation in DATGR?",{"text":84,"@type":76},"The corpus is split into chronological windows, and for each window a weighted graph is constructed from tokenized abstracts. This enables computing normalized edge strengths and tracking their changes across successive time slices.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":21,"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":52,"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":22,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"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":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]