Explore federated learning, a distributed machine learning approach that preserves data privacy, in this 44-minute conference talk from Strange Loop. Learn how this technique enables collaboration on ML models without sharing sensitive data directly. Discover the federated averaging algorithm, real-world challenges, and ongoing research to enhance security, reduce communication costs, and strengthen privacy guarantees. Gain insights into practical applications, potential pitfalls, and strategies for implementing federated learning across various domains, from embedded devices to legal entities. Understand when and how to leverage this technology to balance the benefits of machine learning with crucial privacy concerns.
Overview
Syllabus
Intro
What is ML
Privacy
Data
Hardware
Federated learning
Pseudocode
Lost Curve
Turbofan Tycoon
Hello World
Unequal distribution
The bad things
Does it work
Resources
Problems
Example
Strategies
When to use federated learning
Practical advice
Papers
Taught by
Strange Loop Conference
Tags
Related Courses
-
Private Multi-Task Learning - Formulation and Applications to Federated Learning
-
Federated Learning with Formal User-Level Differential Privacy Guarantees
-
Privacy in Federated Learning at Scale
-
AI Singapore's Journey into the World of Federated Learning
-
Federated Machine Learning with Python
-
Fundamentals of Privacy-Preserving Federated Learning
