Federated Learning with Python

Acquire essential skills to build an authentic federated learning system with Python to bring your machine learning applications to the next level

Key Features

• Design distributed systems that are applied in real-world federated learning applications at scale
• Discover multiple aggregation schemes applicable to various ML settings and applications
• Develop a federated learning system that can be tested in distributed machine learning settings

Book Description

Federated learning (FL) is a paradigm-shifting technology in AI for enabling and accelerating Machine Learning (ML) over private data and must-to-have solutions for most enterprise industries. Thus, it is becoming critical to learn about the foundation of FL with solid coding examples about how the systems work and interact with each other.

Although the concept of FL is relatively simple, it is not just about aggregating collected ML models blindly and bringing the aggregated model back to the distributed agents. We need to know how to design the distributed systems and learning mechanisms carefully to synchronize all the distributed learning processes and synthesis all the locally trained ML models in a consistent manner. That way, you can create a sustainable and resilient FL system that can constantly function in real operation. You will learn all those essential basics in this book.

Therefore, this book goes beyond just describing the conceptual framework or theories of federated learning as seen in many research simulators or prototypes that have been introduced in most of the literature related to this field. Rather, you will learn about the entire design and implementation basics in detail to create your first federated learning system that can be tested in various settings in both local and cloud environments.

What you will learn

• Discover challenges of centralized big data ML today and its solution
• Understand theoretical and conceptual basics of federated learning
• Acquire design and architecting skills to build a federated learning system
• Learn actual implementation of federated learning servers and clients
• Learn how to integrate federated learning into your own ML application
• Understand various aggregation mechanisms for diverse ML scenarios
• Discover popular use cases and future trends of federated learning

Who This Book Is For

This book is for machine learning engineers, data scientists, and AI enthusiasts who want to learn about creating machine learning applications empowered by federated learning. You will need basic knowledge of Python programming and machine learning concepts before you get started with this book.

Table of Contents

1. Challenges in Big Data and Traditional AI
2. What is Federated Learning?
3. Workings of the Federated Learning System
4. Federated Learning Server Implementation with Python
5. Federated Learning Client-Side Implementation
6. Running the Federated Learning System and Analyzing the Results
7. Model Aggregation
8. Introducing the Existing Federated Learning Frameworks
9. Case Studies with Key Use Cases of Federated Learning Applications
10. Future Trends and Development
11. Appendix - Exploring Internal Libraries