[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125292-en":3,"doc-seo-125292-105":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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125292,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Model-Based Machine Learning for Max-Min Fairness Beamforming Design in JCAS Systems","Joint communications and sensing (JCAS) is positioned as a key enabling technology for future wireless systems, where communications and sensing must share limited resources. The work studies multi-user, multi-target beamforming design to ensure fairness while balancing communications and sensing performance. Transmit and receive beamformers are jointly optimized to maximize a weighted sum of the minimum communications rate and sensing mutual information. The resulting non-smooth, non-convex formulation is reformulated for tractability, then solved via alternating optimization and followed by an AO-based model-based learning method. Numerical results demonstrate scalable performance and reduced runtime versus conventional optimization approaches.","Model-Based Machine Learning for Max-Min Fairness Beamforming Design in JCAS Systems  \nMengyuan Ma􀀃 , Tianyu Fang􀀃 , Nir Shlezingery , A. L. Swindlehurstx , Markku Juntti􀀃 , and Nhan Nguyen􀀃  \n􀀃 Centre for Wireless Communications (CWC), University of Oulu, Finland  \ny School of ECE, Ben-Gurion University of the Negev, Beer-Sheva, Israel  \nxDepartment of EECS, University of California, Irvine, CA, USA  \nEmail: fmengyuan.ma, tianyu.fang, markku.juntti, nhan.nguyeng@oulu.fi; [nirshl@bgu.ac.il](nirshl@bgu.ac.il) ; [swindle@uci.edu](swindle@uci.edu)  \nAbstract—Joint communications and sensing (JCAS) is expected to be a crucial technology for future wireless systems. This paper investigates beamforming design for a multi-user multi-target JCAS system to ensure fairness and balance between communications and sensing performance. We jointly optimize the transmit and receive beamformers to maximize the weighted sum of the minimum communications rate and sensing mutual information. The formulated problem is highly challenging due to its non-smooth and non-convex nature. To overcome the challenges, we reformulate the problem into an equivalent but moretractable form. We first solve this problem by alternating optimization (AO) and then propose a machine learning algorithm based on the AO approach. Numerical results show that our scheme scales effectively with the number of the communications users and provides better performance with shorter run time compared to conventional optimization approaches.  \nIndex Terms—Max-min fairness, beamforming, joint communications and sensing , machine learning.  \nI. INTRODUCTION  \nJoint communications and sensing (JCAS) is a pivotal technology for future wireless communications systems, enabling communications and sensing functionalities on a unified hardware platform. This integration facilitates spectrum sharing and reduces hardware costs [1]–[3] . However, the shared and limited resources for these dual functionalities pose significant challenges for JCAS transceiver design [4], [5] . Beamforming plays a key role in addressing this challenge by enhancing spectral efficiency and improving sensing accuracy [6], [7] .  \nRecent literature on beamforming design for JCAS systems has focused on three main optimization goals: maximizing sensing performance, maximizing communications performance, and balancing the tradeoff between them. Sensingoriented designs [8]–[22] optimize sensing while ensuring communication capabilities. In contrast, communicationoriented designs [23]–[25] prioritize communications performance under sensing constraints. Other works [26]–[35] explore the communications-sensing performance tradeoff by maximizing a weighted sum of communications and sensing utility functions. Communications performance is typically measured by rate or SINR, while sensing performance is evaluated using metrics like beampattern matching [8], [11]–[13], SCNR [24], [29], [31], sensing mutual information (MI)  \n[22], [35], and the Cramr–Rao lower bound [15]–[17] .  \nDespite these advances, achieving fairness among multiple communications users and sensing targets remains a significant challenge due to the inherently non-smooth nature of max-min optimization problems [30]–[32] . Conventional optimizationbased approaches [30]–[32] typically result in high complexity  \nand involve numerous algorithm parameters that need to be well tuned to ensure performance. In contrast, model-based machine learning (ML) methodologies [36] facilitate realtime operation and satisfactory performance for beamforming design [5], [37] . For example, beamforming optimizers have been unfolded into into deep learning models in [18]–[20],[28], [33], achieving improved computational efficiency and performance. However, current unfolded algorithms are not applicable for addressing the fairness problem because of their problem-specific network structures. Furthermore, the current literature lacks unfolded learning models specifically designed for ma","cbCaivNxZPya9oTY","https://ap.wps.com/l/cbCaivNxZPya9oTY","pdf",649159,1,5,"English","en",105,"# Introduction\n## Background and motivation for JCAS\n## Beamforming optimization objectives and metrics\n## Fairness challenge and limitations of existing methods\n# System Model and Problem Formulation\n## JCAS system and signal model\n## Communications SINR and channel assumptions","[{\"question\":\"What fairness objective does the paper target in JCAS beamforming design?\",\"answer\":\"It maximizes a weighted sum that includes the minimum communications rate across users together with sensing mutual information, enforcing max-min fairness between communications and sensing performance.\"},{\"question\":\"Why is the proposed optimization problem difficult to solve directly?\",\"answer\":\"The formulation is non-smooth and non-convex due to the max-min structure, leading to challenging optimization behavior and high complexity in conventional approaches.\"},{\"question\":\"How does the proposed method reduce complexity and improve runtime?\",\"answer\":\"The problem is first reformulated into an equivalent but more tractable form and solved with alternating optimization, then a low-complexity model-based machine learning algorithm is developed based on the alternating-optimization framework, enabling faster execution and effective scaling with the number of users.\"}]","Model-Based Machine Learning for Max-Min Fairness Beamforming Design in JCAS Systems | PDF",1785898016,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"model-based-machine-learning-for-max-min-fairness-beamforming-design-in-jcas-systems","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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/model-based-machine-learning-for-max-min-fairness-beamforming-design-in-jcas-systems/125292/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What fairness objective does the paper target in JCAS beamforming design?","Question",{"text":75,"@type":76},"It maximizes a weighted sum that includes the minimum communications rate across users together with sensing mutual information, enforcing max-min fairness between communications and sensing performance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is the proposed optimization problem difficult to solve directly?",{"text":80,"@type":76},"The formulation is non-smooth and non-convex due to the max-min structure, leading to challenging optimization behavior and high complexity in conventional approaches.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed method reduce complexity and improve runtime?",{"text":84,"@type":76},"The problem is first reformulated into an equivalent but more tractable form and solved with alternating optimization, then a low-complexity model-based machine learning algorithm is developed based on the alternating-optimization framework, enabling faster execution and effective scaling with the number of users.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"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":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"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":21,"slug":137},19,"General","general"]