[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127636-en":3,"doc-seo-127636-105":31,"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":28,"seo_description":14,"update_tm":29,"read_time":30},127636,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Graph Neural Networks for Temporal Graphs - State of the Art, Open Challenges, and Opportunities","Graph Neural Networks (GNNs) have become the dominant approach for learning on static graph-structured data, yet many real systems evolve over time as nodes, edges, and attributes change. Recent temporal-graph models extend GNNs, but the literature lacks a unified systematization. This work surveys current temporal GNN state of the art, formalizes learning settings and tasks, and introduces a taxonomy based on how time is represented and processed, concluding with major open research and application challenges.","Graph Neural Networks for Temporal Graphs: State of the Art, Open Challenges, and Opportunities  \nAntonio Longa∗ antonio. longa@unitn. it  \nUniversity of Trento and Fondazione Bruno Kessler, Trento, Italy  \nVeronica Lachi∗ [veronica. lachi@student.unisi.it](veronica. lachi@student.unisi.it)  \nUniversity of Siena, Siena, Italy  \nGabriele Santin∗ [gsantin@fbk. eu](gsantin@fbk. eu)  \nFondazione Bruno Kessler, Trento, Italy  \nMonica Bianchini [monica@diism. unisi.it](monica@diism. unisi.it)  \nUniversity of Siena, Siena, Italy  \nBruno Lepri [lepri@fbk. eu](lepri@fbk. eu)  \nFondazione Bruno Kessler, Trento, Italy  \nPietro Liò [pl219@cam. ac.uk](pl219@cam. ac.uk)  \nUniversity of Cambridge, Cambridge, United Kingdom  \nFranco Scarselli [franco@diism.unisi.it](franco@diism.unisi.it)  \nUniversity of Siena, Siena, Italy  \nAndrea Passerini andrea .passerini@unitn. it  \nUniversity of Trento, Trento, Italy  \nReviewed on OpenReview: [https: // openreview. net/ forum? id= pHCdMat0gI](https: // openreview. net/ forum? id= pHCdMat0gI)  \nAbstract  \nGraph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graph-structured data. However, many real-world systems are dynamic in nature, since the graph and node/edge attributes change over time. In recent years, GNN-based models for temporal graphs have emerged as a promising area of research to extend the capabilities of GNNs. In this work, we provide the first comprehensive overview of the current stateof-the-art of temporal GNN, introducing a rigorous formalization of learning settings and tasks and a novel taxonomy categorizing existing approaches in terms of how the temporal aspect is represented and processed. We conclude the survey with a discussion of the most relevant open challenges for the field, from both research and application perspectives.  \n∗ Equal contribution  \n1 Introduction  \nThe ability to process temporal graphs is becoming increasingly important in a variety of fields such as recommendation systems (Gao et al., 2022a; Wu et al., 2022), social network analysis (Deng et al., 2019; Fan et al., 2019), transportation systems (Jiang & Luo, 2022; Yu et al., 2017), modeling of face-to-face interactions (Longa et al., 2022c), human mobility (Mauro et al., 2022; Gao, 2015), epidemic modeling and contact tracing (Cencetti et al., 2021; So et al., 2020), and many others. Traditional graph-based models are not well suited for analyzing temporal graphs as they assume a fixed structure and are unable to capture its temporal evolution. Therefore, in the last few years, several models capable to directly encode temporal graphs have been developed, such as matrix factorization-based approaches (Ahmed et al. , 2018) and temporal motif-based methods (Longa et al., 2022b) . Recently, also GNNs have been successfully applied to temporal graphs. Indeed, their success in various static graph tasks, including node classification (Hamilton et al., 2017; Veličković et al., 2017; Kipf & Welling, 2016a; Gao et al., 2018; Gasteiger et al. , 2018; Monti et al., 2017; Wu et al., 2019) and link prediction (Zhang & Chen, 2018; Cai & Ji, 2020; Zhang & Chen, 2017), has not only established them as the leading paradigm in static graph processing, but has also indicated the importance of exploring their potential in other graph domains, such as temporal graphs. With approaches ranging from attention-based methods (Xu et al., 2020) to Variational Graph-Autoencoders (VGAEs) (Hajiramezanali et al., 2019), Temporal Graph Neural Networks (TGNNs) have achieved state-ofthe-art results on tasks such as temporal link prediction (Sankar et al., 2020), node classification (Rossi et al. , 2020) and edge classification (Wang et al., 2021a) . Despite the potential of GNN-based models for temporal graph processing and the variety of different approaches that emerged, a systematization of the literature is still missing. Existing surveys either discuss general techniques for learning over temporal grap","cbCaifqLlEbrqg4F","https://ap.wps.com/l/cbCaifqLlEbrqg4F","pdf",630141,2,1,24,"English","en",105,"# Introduction\n# Temporal Graphs\n## Static Graph-SG","[{\"question\":\"Why are temporal graphs important in real-world applications?\",\"answer\":\"Temporal graphs arise when system structure and node/edge attributes change over time, which traditional fixed-graph models cannot capture. The document highlights domains such as recommendation, social networks, transportation, mobility, and epidemic/contact tracing.\"},{\"question\":\"What gap does this work address in temporal GNN research?\",\"answer\":\"The document states that existing surveys either cover only general techniques for temporal graphs, focus on narrow subtopics, or provide broader graph overviews without in-depth treatment of temporal GNNs. It aims to systematize temporal GNN methods with task formalization.\"},{\"question\":\"How does the paper organize existing temporal GNN methods?\",\"answer\":\"It introduces a taxonomy that groups approaches by how the temporal aspect is represented and how it is processed by the model.\"}]","Graph Neural Networks for Temporal Graphs - State of the Art, Open Challenges, and Opportunities | PDF",1785940440,60,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"graph-neural-networks-for-temporal-graphs-state-of-the-art-open-challenges-and-opportunities-127636","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/graph-neural-networks-for-temporal-graphs-state-of-the-art-open-challenges-and-opportunities-127636/127636/",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":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",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},"Why are temporal graphs important in real-world applications?","Question",{"text":76,"@type":77},"Temporal graphs arise when system structure and node/edge attributes change over time, which traditional fixed-graph models cannot capture. The document highlights domains such as recommendation, social networks, transportation, mobility, and epidemic/contact tracing.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What gap does this work address in temporal GNN research?",{"text":81,"@type":77},"The document states that existing surveys either cover only general techniques for temporal graphs, focus on narrow subtopics, or provide broader graph overviews without in-depth treatment of temporal GNNs. It aims to systematize temporal GNN methods with task formalization.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the paper organize existing temporal GNN methods?",{"text":85,"@type":77},"It introduces a taxonomy that groups approaches by how the temporal aspect is represented and how it is processed by the model.","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},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":30,"slug":109},5,"Comic","comic",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]