[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85391-en":3,"doc-seo-85391-105":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},85391,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Research Team Identification Based on Representation Learning of Academic Heterogeneous Information Network","Academic networks describe heterogeneous information networks with multiple node and relation types. Existing representation-learning methods for homogeneous networks cannot exploit such heterogeneity and thus do not transfer directly to academic HINs. To identify and discover scientific research teams from massive, complex scientific and technological data, this paper proposes a representation-learning based team identification approach using node-level and meta-path-level attention. Low-dimensional embeddings preserve topology and meta-path semantics, and teams and key members are selected by maximizing node influence. Experiments validate improved performance.","Research Team Identification Based on Representation Learning of Academic Heterogeneous Information Network  \nJunfu Wang  \nBeijing Key Laboratory of Intelligent Communication Software and Multimedia, School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications Beijing, China  \nYawen Li∗ School of Economics and Management, Beijing University of Posts and Telecommunications Beijing, China  \nZhe Xue  \nBeijing Key Laboratory of Intelligent Communication Software and Multimedia, School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications Beijing, China  \nAng Li  \nBeijing Key Laboratory of Intelligent Communication Software and Multimedia, School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications Beijing, China  \narXiv :2311 .00922v2 [ cs .IR] 11 Jul 2026  \nAbstract  \nAcademic networks in the real world can usually be described by heterogeneous information networks composed of multiple types of nodes and relationships. Existing representation-learning research for homogeneous information networks lacks the ability to explore the heterogeneity of such networks and therefore cannot be directly applied to heterogeneous information networks. To meet the practical need to identify and discover scientific research teams from academic heterogeneous information networks composed of massive and complex scientific and technological data, this paper proposes a research-team identification method based on representation learning. Node-level and meta-path-level attention mechanisms learn low-dimensional, dense, real-valued vector representations while retaining rich topological information and meta-path semantics. Scientific research teams and important team members are then identified by maximizing node influence. Experimental results show that the proposed method outperforms the comparison methods.  \nKeywords  \nacademic heterogeneous information network, representation learning, attention mechanism, node influence maximization, research team identification  \n1 Introduction  \nScientific and technological data, including journal papers, funded projects, and patents, are growing rapidly. Ontology-based retrieval has long supported the organization and access of such information [1], while studies of scientific collaboration describe how research relationships evolve in the information age [2] . These multitype, multi-form, and widely connected data constitute large academic heterogeneous information networks (HINs), including social platforms whose heterogeneous relations support personalized recommendation [3] . Dynamic-interest tracking can further reveal  \n∗ [Corresponding author: warmly0716@126.com](Corresponding author: warmly0716@126.com).  \nchanging scholar groups from multiple views [4], and sentimentvariation modeling shows how temporal changes in large publicevent data can be explained [5] . Because scientific work is increasingly specialized and complex, teamwork has become an important way to advance research. Effectively discovering research teams from large and complex scientific data is therefore an urgent practical need.  \nNetwork embedding preserves proximity and semantic information in large networks. Low-cost incremental learning has been studied for dynamic HINs [6], and semantic-similarity attention combined with hypergraph convolution strengthens scientificpublication representations [7] . HIN embedding has been applied to clustering, classification, link prediction, and recommendation. Relation-structure-aware embedding captures heterogeneous relations [8]; interpretable machine learning can expose the evidence behind intelligent decisions [9]; and graph neural network surveys summarize the broader development of representation learning on graphs [10]. However, many meta-path-based approaches assume that all nodes share the same meta-","cbCaiqwUhChUTGnY","https://ap.wps.com/l/cbCaiqwUhChUTGnY","pdf",2355310,2,1,7,"English","en",105,"# 1 Introduction\n# 2 Related Work","[{\"question\":\"Why can’t homogeneous information network representation learning be directly applied to academic heterogeneous information networks?\",\"answer\":\"Because homogeneous methods lack mechanisms to represent heterogeneity in node and relation types, they cannot properly capture the distinct semantics of academic HINs. The paper motivates a model that jointly preserves topology and meta-path semantics.\"},{\"question\":\"What representation learning approach is proposed for academic HINs?\",\"answer\":\"The method uses node-level and meta-path-level attention mechanisms to learn dense, low-dimensional real-valued embeddings. It retains both topological information and meta-path semantics.\"},{\"question\":\"How are research teams and important members identified in the proposed method?\",\"answer\":\"After obtaining learned representations, the method identifies teams, leaders, and key members by maximizing node influence. Experimental results show it outperforms comparison methods.\"}]",1784203083,18,{"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},"research-team-identification-based-on-representation-learning-of-academic-heterogeneous-information-network","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/research-team-identification-based-on-representation-learning-of-academic-heterogeneous-information-network/85391/",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","2026-07-23","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 can’t homogeneous information network representation learning be directly applied to academic heterogeneous information networks?","Question",{"text":75,"@type":76},"Because homogeneous methods lack mechanisms to represent heterogeneity in node and relation types, they cannot properly capture the distinct semantics of academic HINs. The paper motivates a model that jointly preserves topology and meta-path semantics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What representation learning approach is proposed for academic HINs?",{"text":80,"@type":76},"The method uses node-level and meta-path-level attention mechanisms to learn dense, low-dimensional real-valued embeddings. It retains both topological information and meta-path semantics.",{"name":82,"@type":73,"acceptedAnswer":83},"How are research teams and important members identified in the proposed method?",{"text":84,"@type":76},"After obtaining learned representations, the method identifies teams, leaders, and key members by maximizing node influence. Experimental results show it outperforms comparison methods.","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},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"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":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"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"]