Federated Learning

Privacy and Incentive

AvQiang Yang,Lixin Fan

Häftad, Engelska, 2020

Del 12500 i serien Lecture Notes in Computer Science

949 kr

Beställningsvara. Skickas inom 10-15 vardagar. Fri frakt över 249 kr.

Beskrivning

This book provides a comprehensive and self-contained introduction to federated learning, ranging from the basic knowledge and theories to various key applications.

Produktinformation

Utgivningsdatum:2020-11-26
Mått:155 x 235 x 17 mm
Vikt:452 g
Format:Häftad
Språk:Engelska
Serie:Lecture Notes in Computer Science
Antal sidor:286
Förlag:Springer Nature Switzerland AG
ISBN:9783030630751

Utforska kategorier

Nätverk och kommunikation inom Data och IT
Artificiell intelligens inom Data och IT
Hårdvara inom Data och IT

Innehållsförteckning

Privacy.- Threats to Federated Learning.- Rethinking Gradients Safety in Federated Learning.- Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks.- Task-Agnostic Privacy-Preserving Representation Learning via Federated Learning.- Large-Scale Kernel Method for Vertical Federated Learning.- Towards Byzantine-resilient Federated Learning via Group-wise Robust Aggregation.- Federated Soft Gradient Boosting Machine for Streaming Data.- Dealing with Label Quality Disparity In Federated Learning.- Incentive.- FedCoin: A Peer-to-Peer Payment System for Federated Learning.- Efficient and Fair Data Valuation for Horizontal Federated Learning.- A Principled Approach to Data Valuation for Federated Learning.- A Gamified Research Tool for Incentive Mechanism Design in Federated Learning.- Budget-bounded Incentives for Federated Learning.- Collaborative Fairness in Federated Learning.- A Game-Theoretic Framework for Incentive Mechanism Design in Federated Learning.- Applications.- Federated Recommendation Systems.- Federated Learning for Open Banking.- Building ICU In-hospital Mortality Prediction Model with Federated Learning.- Privacy-preserving Stacking with Application to Cross-organizational Diabetes Prediction.