[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81572-en":3,"doc-seo-81572-105":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},81572,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","RIS-Assisted Downlink Pinching-Antenna Systems GNN-Enabled Optimization Approaches","Investigates a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna system (PASS) for multi-user downlink transmission, motivated by the uncertain effect of combining PASS with RIS in wireless communications. A unified formulation maximizes sum rate (SR) and energy efficiency (EE) under constraints on movable antenna regions, total transmit power, and RIS element phase tunability. A three-stage graph neural network learns PA positions from user locations, RIS phase shifts from composite channel conditions, then determines beamforming vectors. Unsupervised training and integration strategies with convex optimization enable practical inference–optimality trade-offs. Extensive simulations validate performance, generalization, reliability, and real-time applicability, while analyzing key parameter impacts.","RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches  \nChangpeng He, Yang Lu, Member, IEEE, Yanqing Xu, Member, IEEE, Chong-Yung Chi, Fellow, IEEE,  \nand Arumugam Nallanathan, Fellow, IEEE,  \narXiv :2511 .20305v2 [ cs .NI] 10 Jul 2026  \nAbstract—This paper investigates a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna (PA) system (PASS) for multi-user downlink information transmission, motivated by the unknown impact of the integration of emerging PASS and RIS on wireless communications. First, we formulate sum rate (SR) and energy efficiency (EE) maximization problems in a unified framework, subject to constraints on the movable region of PAs, total power budget, and tunable phase of RIS elements. Then, by leveraging a graph-structured topology of the RIS-assisted PASS, a novel three-stage graph neural network (GNN) is proposed, which learns PA positions based on user locations, and RIS phase shifts according to composite channel conditions at the first two stages, respectively, and finally determines beamforming vectors. Specifically, the proposed GNNis achieved through unsupervised training, together with three implementation strategies for its integration with convex optimization, thus offering trade-offs between inference time and solution optimality. Extensive numerical results are provided to validate the effectiveness of the proposed GNN, and to support its unique attributes of viable generalization capability, good performance reliability, and real-time applicability. Moreover, the impact of key parameters on RIS-assisted PASS is illustrated and analyzed.  \nIndex Terms—Reconfigurable intelligent surface, pinchingantenna system, three-stage, graph neural network.  \nI. INTRODUCTION  \nThe evolution toward sixth-generation (6G) wireless networks demands unprecedented data rates, ultra-low latency, and exceptional energy efficiency (EE) to support emerging applications such as holographic communications, digital twins, and the tactile internet [1] . To meet these stringent requirements, novel programmable metasurfaces, which can intelligently reconfigure the wireless propagation environment, have emerged as an essential technology. Among these metasurfaces, the reconfigurable intelligent surfaces (RIS) [2], [3] and the pinching-antenna (PA) systems (PASS) [4], [5] standout as two promising candidates, offering complementary  \nChangpeng He and Yang Lu are with the State Key Laboratory of Advanced Rail Autonomous Operation, and also with the School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China (e-mail: [25110135@bjtu.edu.cn](25110135@bjtu.edu.cn), [yanglu@bjtu.edu.cn](yanglu@bjtu.edu.cn)).  \nYanqing Xu is with the School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, 518172, China (email: xuyan[qing@cuhk.edu.cn](qing@cuhk.edu.cn)).  \nChong-Yung Chi is with the Institute of Communications Engineering, Department of Electrical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan (e-mail: [cychi@ee.nthu.edu.tw](cychi@ee.nthu.edu.tw)).  \nArumugam Nallanathan is with the School of Electronic Engineering and Computer Science, Queen Mary University of London, London and also with the Department of Electronic Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, South Korea (e-mail: [a.nallanathan@qmul.ac.uk](a.nallanathan@qmul.ac.uk)).  \nadvantages for future wireless networks. On one hand, RIS utilizes a large array of passive reflecting elements with adjustable phase shifts to intelligently construct cascade wireless links to enable signal strength enhancement, interference suppression, coverage extension, and obstacle bypassing [7] . The passive nature of RIS elements ensures low power consumption and cost-effective deployment, making it particularly suitable for energy-constrained scenarios [8] . Recent studies have demonstrated significant performance gains in RISassiste","cbCaiufjQyoLQcZJ","https://ap.wps.com/l/cbCaiufjQyoLQcZJ","pdf",1052386,5,1,13,"English","en",105,"# Abstract\n# Introduction\n## Motivation: 6G requirements\n## Key technologies: RIS and PASS\n## Synergistic integration challenges\n# Deep learning for wireless optimization","[{\"question\":\"What problem does the paper address in RIS-assisted downlink transmission?\",\"answer\":\"It targets multi-user downlink information transmission in a RIS-assisted pinching-antenna system, focusing on how to optimize jointly coupled decisions when integrating PASS and RIS.\"},{\"question\":\"How are the optimization objectives and constraints defined?\",\"answer\":\"The work formulates sum rate (SR) and energy efficiency (EE) maximization within a unified framework, constrained by PA movable regions, total power budget, and tunable RIS phase shifts.\"},{\"question\":\"What is the role of the three-stage GNN in the proposed solution?\",\"answer\":\"The GNN uses a graph-structured topology to learn PA positions from user locations, determine RIS phase shifts from composite channel conditions, and finally output beamforming vectors, with unsupervised training and integration strategies for practical deployment.\"}]",1784174396,33,{"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},"ris-assisted-downlink-pinching-antenna-systems-gnn-enabled-optimization-approaches","",{"@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/ris-assisted-downlink-pinching-antenna-systems-gnn-enabled-optimization-approaches/81572/",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","2026-07-25","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 problem does the paper address in RIS-assisted downlink transmission?","Question",{"text":76,"@type":77},"It targets multi-user downlink information transmission in a RIS-assisted pinching-antenna system, focusing on how to optimize jointly coupled decisions when integrating PASS and RIS.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are the optimization objectives and constraints defined?",{"text":81,"@type":77},"The work formulates sum rate (SR) and energy efficiency (EE) maximization within a unified framework, constrained by PA movable regions, total power budget, and tunable RIS phase shifts.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the role of the three-stage GNN in the proposed solution?",{"text":85,"@type":77},"The GNN uses a graph-structured topology to learn PA positions from user locations, determine RIS phase shifts from composite channel conditions, and finally output beamforming vectors, with unsupervised training and integration strategies for practical deployment.","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":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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]