[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290181-105":59,"doc-detail-290181-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","graph-representation-learning-tutorial-paper","Graph Representation Learning - Tutorial paper","","Graph Representation Learning focuses on representing real-world examples as graphs to preserve information that would be lost with simpler formats. It highlights how Deep Graph Networks (DGNs) have become a central approach for learning representations from graph-structured inputs. The work reviews core concepts, surveys open research challenges, and summarizes published contributions accepted for the ESANN 2023 special session on graph representation learning.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/graph-representation-learning-tutorial-paper/290181/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/graph-representation-learning-tutorial-paper/290181.png","ImageObject",300,407,{"name":92,"@type":93},"Himbo","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is representing examples as graphs important in machine learning?","Question",{"text":112,"@type":113},"Graph representations help avoid information loss by capturing relations and structure naturally present in real-world data.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What are Deep Graph Networks (DGNs) used for?",{"text":117,"@type":113},"DGNs learn graph-based representations that support tasks on nodes, edges, or entire graphs, and they are widely used as standard models for graph-structured inputs.",{"name":119,"@type":110,"acceptedAnswer":120},"How is a graph formally defined in the paper?",{"text":121,"@type":113},"A static graph is formalized as g = (V, E, X, A), where V is the set of nodes, E the set of edges, and X and A represent node and edge feature domains or attributes.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},290181,1791469163,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":4},687197100911,"https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697","Graph Representation Learning  \nDavide Bacciu 1 , Federico Errica2 , Alessio Micheli 1 , Nicol`o Navarin3 , Luca Pasa3 , Marco Podda 1 and Daniele Zambon4  \n1-Department of Computer Science, University of Pisa, Italy 2-NEC Laboratories Europe, Germany 3-Department of Mathematics, University of Padova, Italy 4-The Swiss AI Lab IDSIA & Universit`a della Svizzera italiana, Switzerland  \nAbstract. In a broad range of real-world machine learning applications, representing examples as graphs is crucial to avoid a loss of information.  \nFor this reason, in the last few years, the definition of machine learning methods, particularly neural networks, for graph-structured inputs has been gaining increasing attention. In particular, Deep Graph Networks (DGNs) are nowadays the most commonly adopted models to learn a representation that can be used to address different tasks related to nodes, edges, or even entire graphs. This tutorial paper reviews fundamental concepts and open challenges of graph representation learning and summarizes the contributions that have been accepted for publication to the ESANN 2023 special session on the topic.  \n1 Introduction  \nIn this tutorial paper, we introduce the core concepts related to Graph Representation Learning, which is the subject of a special session organized by the authors at the 31th European Symposium on Artificial Neural Networks, Computational Intelligence, and Machine Learning. Many critical real-world applications produce data that can be naturally represented by complex structures such as graphs. Graphs are particularly suited to represent relations (edges) between the components (nodes) constituting an entity.  \nIn this paper, we focus our attention on applying Deep Learning models for learning in graph domains, where Deep Graph Networks (DGNs) [1] are nowadays the de facto standard. The origins of DGNs can be traced back to works on directed acyclic graphs [2, 3], where recursive neural networks were used to automatically extract information from structured data to solve the task at hand. Current DGNs are capable of modeling cyclic graphs, and the pioneering methods for this class of models are based on the recurrent [4] and convolutional [5] paradigms of computation.  \nDGNs are composed by several layers that can learn representations that embed information about the entities and their relations. The DGNs can be divided into three broad categories: (i) the models inspired by neural architectures [6, 7, 8, 9], (ii) the probabilistic models of graphs [10], and (iii) the hybrid models that leverage both neural and probabilistic models to generate graphs [11] .  \nGraph-structured data are ubiquitous in nature, therefore there are a vast number of possible real-world applications of DGNs. These applications can  \nFig. 1: Carbonic acid molecule represented as a 2D graph where nodes denote atoms with their type. The neighborhood Nu of node u is marked by the green dashed area. Edges represent single or double bonds.  \nbe associated with nodes, edges, or properties of entire graphs. One of the most common applications of DGNs concerns the predictions over nodes in a network. An example in this setting is the prediction of properties of a social network user based on his connections. Another related task involves discovering the relationships in a social network by performing an edge-level prediction task. Finally, DGNs can also be used to tackle graph-level prediction tasks. In this setting, each example is composed of a whole graph, and the learning tasks are predictions of the properties of the whole graphs. An example is the prediction of the toxicity in humans of chemical compounds represented by their molecular graph, of which we show an example in Figure 1 .  \n2 Background Notions  \nBefore describing the functioning of graph representation learning methods, we first present basic definitions about graphs that are used in the contributions of this special session. A commonly used forma","cbCailh1pxPTl5Ig","https://ap.wps.com/l/cbCailh1pxPTl5Ig","pdf",1590764,"English","# Introduction\n## Deep Graph Networks overview\n# Background Notions\n## Graph definitions and formalization\n## Adjacency matrix and sparse graphs\n## Neighborhood and adjacency list concepts","[{\"question\":\"Why is representing examples as graphs important in machine learning?\",\"answer\":\"Graph representations help avoid information loss by capturing relations and structure naturally present in real-world data.\"},{\"question\":\"What are Deep Graph Networks (DGNs) used for?\",\"answer\":\"DGNs learn graph-based representations that support tasks on nodes, edges, or entire graphs, and they are widely used as standard models for graph-structured inputs.\"},{\"question\":\"How is a graph formally defined in the paper?\",\"answer\":\"A static graph is formalized as g = (V, E, X, A), where V is the set of nodes, E the set of edges, and X and A represent node and edge feature domains or attributes.\"}]","Graph Representation Learning - Tutorial paper | PDF",1789640881,25]