Federated Learning: Fundamentals and Advances

Jin, Yaochu; Zhu, Hangyu; Xu, Jinjin

ISBN 10: 981197084X / ISBN 13: 9789811970849

Edité par Springer, 2022

A propos de cet article

In.

N° de réf. du vendeur ria9789811970849_new

Détails bibliographiques

• Titre: Federated Learning: Fundamentals and Advances
• Éditeur: Springer
• Date de parution: 2022
• Langue: anglais
• ISBN à 10 chiffres: 981197084X
• ISBN à 13 chiffres: 9789811970849
• Reliure: Couverture souple
• État de l'article: New

A propos de ce titre

Synopsis

1. Introduction

1.1 Artificial neural networks and deep learning

1.2 Evolutionary optimization and learning

1.3 Privacy-preserving computation

1.4 Federated learning

1.5 Summary

1. Communication-Efficient Federated Learning

2.1 Communication cost in federated learning

2.2 Main methodologies

2.3 Temporally weighted averaging and layer-wise weight update

2.4 Trained ternary compression for federated learning

2.5 Summary

Evolutionary Federated Learning

3.1 Motivations and challenges

3.2 Offline evolutionary multi-objective federated learning

3.3 Realtime evolutionary federated neural architecture search

3.4 Summary

Secure Federated Learning

4.1 Threats to federated learning

4.2 Distributed encryption for horizontal federated learning

4.3 Secure vertical federated learning

4.4 Summary

Summary and Outlook

5.1 Summary

5.2 Future directions