[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85077-en":3,"doc-seo-85077-105":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},85077,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning","Federated learning at the edge is constrained by communication bandwidth, motivating one-shot aggregation that reduces interaction rounds while avoiding server-heavy iterative fine-tuning and distillation. Analytical federated learning further reduces cost via gradient-free least-squares closed-form aggregation, but its fixed feature assumptions break under non-IID data, causing feature manifold misalignment and degraded accuracy. FedOPAL rectifies heterogeneous feature distributions using visual prompt tuning as learned feature rectifiers with local proximal constraints. Experiments show major gains over analytical baselines and accuracy comparable to state-of-the-art iterative methods while keeping zero server-side training costs.","FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning  \nLingyu Qiu, Daniela Annunziata, Stefano Izzo, Fabio Giampaolo, Francesco Piccialli†  \nDepartment of Mathematics and Applications “R. Caccioppoli”, University of Naples Federico II, Italy  \n{lingyu.qiu, daniela.annunziata, stefano.izzo, fabio.giampaolo, [francesco.piccialli](francesco.piccialli}@unina.it)[}](francesco.piccialli}@unina.it)[@unina.it](francesco.piccialli}@unina.it)  \narXiv :2607 .08368v 1 [ cs .AI] 9 Jul 2026  \nAbstract—With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates this problem by minimizing communication rounds, existing iterative fine-tuning or knowledge distillation methods still face challenges such as high server-side computational costs and hyperparameter sensitivity. Analytical federated learning achieves efficient gradientfree aggregation using least-squares closed-form solutions, but in environments with non-independent and identically distributed data, its static feature assumptions fail, leading to feature manifold misalignment and severely impairing model performance. To address this contradiction, this paper proposes the FedOPAL framework. This framework adapts the visual promptsas feature rectifiers, actively correcting the feature distribution of heterogeneous data to a linearly separable space by applying local proximal constraints, thereby satisfying the theoretical assumptions of analytical federated learning. Experimental results show that FedOPAL not only significantly outperforms the original analytical methods on several benchmarks, but also achieves accuracy comparable to state-of-the-art iterative methods while maintaining zero server-side training costs, providing a new engineering paradigm for efficient collaboration of large modelson the edge.  \nIndex Terms—One-Shot Federated Learning, Federated Learning, Prompt Learning, Vision Language Model  \nI. INTRODUCTION  \nFederated Learning (FL) has achieved significant success asa privacy-preserving distributed machine learning paradigm, particularly in medical image analysis [1], financial risk control [2], and the Internet of Things (IoT) [3] . However, deep learning is currently transitioning into the era of largescale pre-trained foundation models, leading to an exponential increase in model parameters. For instance, deploying models like ViT [4] and CLIP [5] significantly increases the communication overhead between edge devices and servers. Meanwhile, relying on simple networks is no longer sufficient to meet the growing performance demands of modern industry [6] . In scenarios with limited bandwidth or unstable connections, such as autonomous vehicles or satellite communications, the highfrequency parameter interaction required by the traditional federated averaging algorithm FedAvg has become computationally prohibitive [7] . Therefore, realizing One-Shot Federated Learning (OFL) that can complete model aggregation with  \n† Corresponding author.  \nCode is available at: [https://github.com/Lynn0925/FLICS](https://github.com/Lynn0925/FLICS)  \nonly one communication round has become a key technology to break through this bottleneck [8] .  \nTo achieve single-round aggregation, existing research methods, such as those based on knowledge distillation [9]–[11] and data synthesis approaches [12], typically employ server-side retraining. In these approaches, clients upload model parameters or generators, and the server utilizes public datasets or synthetic data to integrate knowledge via iterative optimization (e.g., ensemble distillation) . While this strategy successfully circumvents multiple communication rounds, it merely shifts the computational burden from the edge to the server, rather than reducing the overall system load.  \nRecently, statistical computation methods based on pretrained models h","cbCailok00NWVwe0","https://ap.wps.com/l/cbCailok00NWVwe0","pdf",571752,2,1,7,"English","en",105,"# Introduction\n## Motivation and Communication Bottlenecks\n## Limitations of Existing One-Shot Methods\n## Analytical OFL and the Non-IID Misalignment Problem\n# FedOPAL Framework\n## Visual Prompt Tuning for Feature Rectification\n## Contributions","[{\"question\":\"为什么在边缘侧进行联邦学习会遇到通信瓶颈？\",\"answer\":\"基础模型在边缘部署会显著增加与服务器之间的交互开销，而传统联邦平均需要高频参数交互，通信带宽受限时会变得计算上难以承受。\"},{\"question\":\"现有迭代式微调或知识蒸馏的一次性联邦学习方法存在哪些问题？\",\"answer\":\"虽然一次性联邦学习减少了通信轮次，但这些方法通常仍需要在服务器端进行再训练或迭代优化，从而带来较高的服务器计算成本，并且对超参数较敏感。\"},{\"question\":\"FedOPAL如何解决解析式一次性联邦学习在非IID场景下的特征失配？\",\"answer\":\"FedOPAL在冻结的视觉基础模型前注入可学习的视觉提示token，将其作为特征校正器，并通过局部近端约束引导异构数据映射到线性可分的空间，从而满足解析式聚合的理论假设。\"}]",1784200905,18,{"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},"fedopal-one-shot-federated-learning-via-analytic-visual-prompt-tuning","",{"@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/fedopal-one-shot-federated-learning-via-analytic-visual-prompt-tuning/85077/",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","2026-07-24","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},"为什么在边缘侧进行联邦学习会遇到通信瓶颈？","Question",{"text":75,"@type":76},"基础模型在边缘部署会显著增加与服务器之间的交互开销，而传统联邦平均需要高频参数交互，通信带宽受限时会变得计算上难以承受。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"现有迭代式微调或知识蒸馏的一次性联邦学习方法存在哪些问题？",{"text":80,"@type":76},"虽然一次性联邦学习减少了通信轮次，但这些方法通常仍需要在服务器端进行再训练或迭代优化，从而带来较高的服务器计算成本，并且对超参数较敏感。",{"name":82,"@type":73,"acceptedAnswer":83},"FedOPAL如何解决解析式一次性联邦学习在非IID场景下的特征失配？",{"text":84,"@type":76},"FedOPAL在冻结的视觉基础模型前注入可学习的视觉提示token，将其作为特征校正器，并通过局部近端约束引导异构数据映射到线性可分的空间，从而满足解析式聚合的理论假设。","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"]