YouTube Live link: 

https://www.youtube.com/watch?v=fNrVh2RWVTc&feature=youtu.be

 
Colab Notebooks:

In order to better prepare for our tutorials, please open and make a copy the colab notebooks and make sure you can run it in Colab. To edit the colab notebook, please go to "File" -> "Save a copy in Drive".

User Copy:
  1. TFF for Image Classification and Text Generation
  2. TFF for Model and Update Compression
  3. Building your own Federated Learning Algorithm 
Full Copy:
  1. TFF for Image Classification and Text Generation
  2. TFF for Model and Update Compression
  3. Building your own Federating Learning Algorithm
 
Dory Q&A:

https://dory.withgoogle.com/series/101456347

If you do not have access, please enter your GSuite or gmail address here.

 

 

Federated Learning Workshop using TensorFlow Federated

Introduction to Federated Learning and Analytics with TFF: Sometimes centrally collecting data produced by edge devices, such as mobile phones or cars, is infeasible or undesirable. With federated learning, clients collaboratively train a model under the direction of a server, while keeping the training data decentralized and mitigating privacy risks. Learn how you can use TensorFlow Federated, an open-source framework for machine learning and other computations on decentralized data, to explore federated learning. In this workshop, you will train an image classification model and a text generation model while learning about the unique advantages and challenges of the federated setting. You will also see examples of how TFF can be used to enable new research. After this tutorial, you will be equipped to further experiment with federated learning on your own. 

TFF for Federated Learning Research: TFF is an extensible, powerful framework for conducting federated learning (FL) research by simulating federated computations on realistic proxy datasets. In this tutorial session, we'll describe the main concepts, components and detailed guidance for conducting different kinds of research in TFF. We'll demonstrate optimization and compression algorithms as examples but also introduce advanced techniques for customizing TFF for various research needs. This tutorial also served as a great starting point for people who are interested to explore the TFF research directory. Note that this tutorial session assumes the audience is familiar with FL layers of TensorFlow Federated.

Our tutorials will assume basic TensorFlow knowledge. For a TensorFlow quickstart, please check out this tutorial, for machine learning using Keras, please check out this tutorial, for more tutorials for TensorFlow, please visit tensorflow.org/tutorials.

When and where

Friday, July 31 | 9:00 AM - 12:30 PM PST
YouTube Live

Questions? Email federatedlearning-workshop2020@google.com

Organized by: Adria Gascon, Marco Gruteser, Peter Kairouz, Zheng Xu, Rainier Aliment, and Jennifer Ye

Community Guidelines

At Google, we celebrate diversity and inclusion — we celebrate it, support it and thrive on it. Google’s philosophy is that all employees and visitors are entitled to a positive environment where everyone can be a successful contributor. We are dedicated to providing a harassment-free and inclusive event experience for everyone. While attending Google events, please remember: Respect each other - Treat everyone with respect. We are committed to a supportive work environment, where everyone has the opportunity to reach their fullest potential. Google has a ZERO TOLERANCE POLICY for harassment of any kind. Speak up if you see or hear something. For more information on our community guidelines, please visit goo.gl/FtOxHM