Trustworthy Federated Learning: First International Workshop, FL 2022, Held in Conjunction with IJCAI 2022, Vienna, Austria, July 23, 2022, Revised Selected Papers

This book presents the refereed proceedings of the First International Workshop on FL 2022, held in Vienna, Austria, during July 23-25, 2022. It includes 11 full papers on topics such as answer set programming, adaptive expert models, and privacy-preserving federated cross-domain social recommendation, with papers selected from 12 submissions.

Format: Paperback / softback
Length: 159 pages
Publication date: 29 March 2023
Publisher: Springer International Publishing AG

This book is a compilation of the refereed proceedings of the First International Workshop, FL 2022, held in conjunction with IJCAI 2022, in Vienna, Austria, from July 23 to 25, 2022. The workshop brought together experts from various fields to discuss and explore innovative approaches in the areas of answer set programming, adaptive expert models for personalization in federated learning, and privacy-preserving federated cross-domain social recommendation.

The 11 full papers presented in this book underwent rigorous review and selection from a total of 12 submissions. These papers are organized into three topical sections:

Answer Set Programming: This section focuses on developing algorithms and techniques for solving answer set programming problems, which are a fundamental aspect of logic programming. The papers in this section explore various approaches, such as constraint solving, model counting, and solving with databases.

Adaptive Expert Models for Personalization in Federated Learning: This section explores the use of adaptive expert models in federated learning settings, where multiple parties share data and collaborate to train a model. The papers in this section discuss the challenges of personalization, such as data heterogeneity, privacy preservation, and model adaptation.

Privacy-Preserving Federated Cross-Domain Social Recommendation: This section focuses on developing privacy-preserving techniques for federated cross-domain social recommendation, where users are interested in recommendations from different domains or sources. The papers in this section explore various approaches, such as differential privacy, k-anonymization, and secure multi-party computation.

Each paper in this book provides detailed insights and innovative solutions to the challenges faced in the respective areas. The contributions made by the authors and reviewers are invaluable in advancing the state-of-the-art in these fields.

We hope that this book will serve as a valuable resource for researchers, practitioners, and students interested in the areas of answer set programming, adaptive expert models, federated learning, and privacy-preserving techniques.

Weight: 273g
Dimension: 235 x 155 (mm)
ISBN-13: 9783031289958
Edition number: 1st ed. 2023