| Description |
1 online resource (209 pages) |
| Series |
Synthesis Lectures on Artificial Intelligence and Machine Learning Ser |
|
Synthesis Lectures on Artificial Intelligence and Machine Learning Ser
|
| Contents |
Intro -- Preface -- Acknowledgments -- Introduction -- Motivation -- Federated Learning as a Solution -- The Definition of Federated Learning -- Categories of Federated Learning -- Current Development in Federated Learning -- Research Issues in Federated Learning -- Open-Source Projects -- Standardization Efforts -- The Federated AI Ecosystem -- Organization of this Book -- Background -- Privacy-Preserving Machine Learning -- PPML and Secure ML -- Threat and Security Models -- Privacy Threat Models -- Adversary and Security Models -- Privacy Preservation Techniques |
|
Secure Multi-Party Computation -- Homomorphic Encryption -- Differential Privacy -- Distributed Machine Learning -- Introduction to DML -- The Definition of DML -- DML Platforms -- Scalability-Motivated DML -- Large-Scale Machine Learning -- Scalability-Oriented DML Schemes -- Privacy-Motivated DML -- Privacy-Preserving Decision Trees -- Privacy-Preserving Techniques -- Privacy-Preserving DML Schemes -- Privacy-Preserving Gradient Descent -- Vanilla Federated Learning -- Privacy-Preserving Methods -- Summary -- Horizontal Federated Learning -- The Definition of HFL -- Architecture of HFL |
|
The Client-Server Architecture -- The Peer-to-Peer Architecture -- Global Model Evaluation -- The Federated Averaging Algorithm -- Federated Optimization -- The FedAvg Algorithm -- The Secured FedAvg Algorithm -- Improvement of the FedAvg Algorithm -- Communication Efficiency -- Client Selection -- Related Works -- Challenges and Outlook -- Vertical Federated Learning -- The Definition of VFL -- Architecture of VFL -- Algorithms of VFL -- Secure Federated Linear Regression -- Secure Federated Tree-Boosting -- Challenges and Outlook -- Federated Transfer Learning |
|
Heterogeneous Federated Learning -- Federated Transfer Learning -- The FTL Framework -- Additively Homomorphic Encryption -- The FTL Training Process -- The FTL Prediction Process -- Security Analysis -- Secret Sharing-Based FTL -- Challenges and Outlook -- Incentive Mechanism Design for Federated Learning -- Paying for Contributions -- Profit-Sharing Games -- Reverse Auctions -- A Fairness-Aware Profit Sharing Framework -- Modeling Contribution -- Modeling Cost -- Modeling Regret -- Modeling Temporal Regret -- The Policy Orchestrator -- Computing Payoff Weightage -- Discussions |
|
Federated Learning for Vision, Language, and Recommendation -- Federated Learning for Computer Vision -- Federated CV -- Related Works -- Challenges and Outlook -- Federated Learning for NLP -- Federated NLP -- Related Works -- Challenges and Outlook -- Federated Learning for Recommendation Systems -- Recommendation Model -- Federated Recommendation System -- Related Works -- Challenges and Outlook -- Federated Reinforcement Learning -- Introduction to Reinforcement Learning -- Policy -- Reward -- Value Function -- Model of the Environment -- RL Background Example |
| Notes |
Reinforcement Learning Algorithms |
|
Print version record |
| Subject |
Machine learning.
|
|
Machine learning
|
| Form |
Electronic book
|
| Author |
Liu, Yang
|
|
Cheng, Yong
|
|
Kang, Yan
|
|
Chen, Tianjian
|
|
Yu, Han
|
| ISBN |
9781681736983 |
|
1681736985 |
|
