Trustworthy Federated Learning [[electronic resource] ] : First International Workshop, FL 2022, Held in Conjunction with IJCAI 2022, Vienna, Austria, July 23, 2022, Revised Selected Papers / / edited by Randy Goebel, Han Yu, Boi Faltings, Lixin Fan, Zehui Xiong

• Pubblicazione: Cham : , : Springer International Publishing : , : Imprint : Springer, , 2023
• Edizione: 1st ed. 2023.
• Descrizione fisica: 1 online resource (168 pages) : illustrations
• Disciplina: 006.3
• Soggetto topico: Artificial intelligence; Data protection; Social sciences—Data processing; Application software; Artificial Intelligence; Data and Information Security; Computer Application in Social and Behavioral Sciences; Computer and Information Systems Applications
• Persona (resp. second.): YuHan (Assistant Professor); GoebelRandy; FaltingsBoi; FanLixin (Scientist); XiongZehui
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Adaptive Expert Models for Personalization in Federated Learning -- Federated Learning with GAN-based Data Synthesis for Non-iid Clients -- Practical and Secure Federated Recommendation with Personalized Mask -- A General Theory for Client Sampling in Federated Learning -- Decentralized adaptive clustering of deep nets is beneficial for client collaboration -- Sketch to Skip and Select: Communication Efficient Federated Learning using Locality Sensitive Hashing -- Fast Server Learning Rate Tuning for Coded Federated Dropout -- FedAUXfdp: Differentially Private One-Shot Federated Distillation -- Secure forward aggregation for vertical federated neural network -- Two-phased Federated Learning with Clustering and Personalization for Natural Gas Load Forecasting -- Privacy-Preserving Federated Cross-Domain Social Recommendation.
• Sommario/riassunto: This book constitutes the refereed proceedings of the First International Workshop, FL 2022, Held in Conjunction with IJCAI 2022, held in Vienna, Austria, during July 23-25, 2022. The 11 full papers presented in this book were carefully reviewed and selected from 12 submissions. They are organized in three topical sections: answer set programming; adaptive expert models for personalization in federated learning and privacy-preserving federated cross-domain social recommendation.
• Titolo autorizzato: Trustworthy Federated Learning
• ISBN: 9783031289965; 9783031289958
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 996517751703316
• Lo trovi qui: Univ. di Salerno
• Serie: Lecture Notes in Artificial Intelligence, . 2945-9141 ; ; 13448