arXiv:2511.15990v1 Announce Type: cross 
Abstract: Digital agriculture is transforming the way we grow food by utilizing technology to make farming more efficient, sustainable, and productive. This modern approach to agriculture generates a wealth of valuable data that could help address global food challenges, but farmers are hesitant to share it due to privacy concerns. This limits the extent to which researchers can learn from this data to inform improvements in farming. This paper presents the Digital Agriculture Sandbox, a secure online platform that solves this problem. The platform enables farmers (with limited technical resources) and researchers to collaborate on analyzing farm data without exposing private information. We employ specialized techniques such as federated learning, differential privacy, and data analysis methods to safeguard the data while maintaining its utility for research purposes. The system enables farmers to identify similar farmers in a simplified manner without needing extensive technical knowledge or access to computational resources. Similarly, it enables researchers to learn from the data and build helpful tools without the sensitive information ever leaving the farmer's system. This creates a safe space where farmers feel comfortable sharing data, allowing researchers to make important discoveries. Our platform helps bridge the gap between maintaining farm data privacy and utilizing that data to address critical food and farming challenges worldwide.

تُحدث الزراعة الرقمية ثورة في إنتاج الغذاء من خلال الاستفادة من التكنولوجيا لتحسين الكفاءة والاستدامة والإنتاجية. ومع ذلك، يتردد المزارعون في مشاركة البيانات القيمة بسبب مخاوف تتعلق بالخصوصية، مما يعيق التقدم في البحث. تُقدم منصة Digital Agriculture Sandbox كمنصة آمنة عبر الإنترنت تسهل التعاون بين المزارعين والباحثين، باستخدام تقنيات مثل التعلم الفيدرالي والخصوصية التفاضلية لحماية المعلومات الحساسة مع السماح بتحليل البيانات.

La agricultura digital está revolucionando la producción de alimentos al aprovechar la tecnología para mejorar la eficiencia, la sostenibilidad y la productividad. Sin embargo, los agricultores son reacios a compartir datos valiosos debido a preocupaciones de privacidad, lo que obstaculiza los avances en la investigación. Se presenta el Digital Agriculture Sandbox como una plataforma en línea segura que facilita la colaboración entre agricultores e investigadores, utilizando técnicas como el aprendizaje federado y la privacidad diferencial para proteger la información sensible mientras se perm…

L'agriculture numérique révolutionne la production alimentaire en utilisant la technologie pour améliorer l'efficacité, la durabilité et la productivité. Cependant, les agriculteurs hésitent à partager des données précieuses en raison de préoccupations liées à la vie privée, ce qui freine les avancées en recherche. Le Digital Agriculture Sandbox est présenté comme une plateforme en ligne sécurisée qui facilite la collaboration entre agriculteurs et chercheurs, utilisant des techniques telles que l'apprentissage fédéré et la confidentialité différentielle pour protéger les informations sensible…

Digital agriculture is revolutionizing food production by leveraging technology to enhance efficiency, sustainability, and productivity. However, farmers are reluctant to share valuable data due to privacy concerns, hindering research advancements. The Digital Agriculture Sandbox is introduced as a secure online platform that facilitates collaboration between farmers and researchers, utilizing techniques like federated learning and differential privacy to protect sensitive information while enabling data analysis.

Digital Agriculture Sandbox for Collaborative Research

arXiv:2511.16423v1 Announce Type: cross 
Abstract: Efficient and lightweight adaptation of pre-trained Vision-Language Models (VLMs) to downstream tasks through collaborative interactions between local clients and a central server is a rapidly emerging research topic in federated learning. Existing adaptation algorithms are typically trained iteratively, which incur significant communication costs and increase the susceptibility to potential attacks. Motivated by the one-shot federated training techniques that reduce client-server exchanges to a single round, developing a lightweight one-shot federated VLM adaptation method to alleviate these issues is particularly attractive. However, current one-shot approaches face certain challenges in adapting VLMs within federated settings: (1) insufficient exploitation of the rich multimodal information inherent in VLMs; (2) lack of specialized adaptation strategies to systematically handle the severe data heterogeneity; and (3) requiring additional training resource of clients or server. To bridge these gaps, we propose a novel Training-free One-shot Federated Adaptation framework for VLMs, named TOFA. To fully leverage the generalizable multimodal features in pre-trained VLMs, TOFA employs both visual and textual pipelines to extract task-relevant representations. In the visual pipeline, a hierarchical Bayesian model learns personalized, class-specific prototype distributions. For the textual pipeline, TOFA evaluates and globally aligns the generated local text prompts for robustness. An adaptive weight calibration mechanism is also introduced to combine predictions from both modalities, balancing personalization and robustness to handle data heterogeneity. Our method is training-free, not relying on additional training resources on either the client or server side. Extensive experiments across 9 datasets in various federated settings demonstrate the effectiveness of the proposed TOFA method.

تناقش الورقة المعنونة 'TOFA: التكيف الفيدرالي من لقطة واحدة بدون تدريب لنماذج الرؤية-اللغة' طريقة جديدة لتكييف نماذج الرؤية-اللغة المدربة مسبقًا مع مهام محددة من خلال التعلم الفيدرالي. تهدف هذه الطريقة إلى تقليل تكاليف الاتصال وتعزيز الكفاءة من خلال السماح للعملاء المحليين بالتفاعل مع خادم مركزي في جولة واحدة، مما يعالج التحديات مثل تباين البيانات وعدم الاستفادة الكافية من المعلومات متعددة الوسائط.

El artículo titulado 'TOFA: Adaptación Federada de Una Sola Toma Sin Entrenamiento para Modelos de Visión-Lenguaje' discute un método novedoso para adaptar modelos de visión-lenguaje preentrenados a tareas específicas mediante el aprendizaje federado. Este enfoque busca reducir los costos de comunicación y mejorar la eficiencia al permitir que los clientes locales interactúen con un servidor central en una sola ronda, abordando desafíos como la heterogeneidad de datos y la subutilización de información multimodal.

L'article intitulé 'TOFA: Adaptation fédérée en une seule fois sans formation pour les modèles de vision-langage' aborde une méthode novatrice pour adapter des modèles de vision-langage pré-entraînés à des tâches spécifiques en utilisant l'apprentissage fédéré. Cette approche vise à réduire les coûts de communication et à améliorer l'efficacité en permettant aux clients locaux d'interagir avec un serveur central en un seul tour, tout en répondant aux défis tels que l'hétérogénéité des données et la sous-utilisation des informations multimodales.

The paper titled 'TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models' discusses a novel method for adapting pre-trained Vision-Language Models (VLMs) to specific tasks using federated learning. This approach aims to reduce communication costs and enhance efficiency by allowing local clients to interact with a central server in a single round, addressing challenges such as data heterogeneity and the underutilization of multimodal information.

Digital Agriculture Sandbox for Collaborative Research

Was this article worth reading? Share it