Google has today introduced federated analytics, the practice of applying data science methods to the analysis of raw data that is stored locally on users’ devices.
By doing so, the search giant hopes to bypass data privacy concerns. Google’s AI research team has talked about this new method on its official blog.
The writers have pointed out that like federated learning, it works by running local computations over each device’s data, and only making the aggregated results — and never any data from a particular device — available to product engineers.
Unlike federated learning, however, federated analytics aims to support basic data science needs.
The post has described the basic methodologies of federated analytics that were developed in the pursuit of federated learning, how Google then extended those insights into new domains, & how recent advances in federated technologies enabled better accuracy & privacy for a growing range of data science needs.
Federated learning, introduced in 2017, enables developers to train machine learning (ML) models across many devices without centralized data collection, ensuring that only the user has a copy of their data.
It was used to power experiences like suggesting next words & expressions in Gboard for Android & improving the quality of smart replies in Android Messages.
Following the success of these applications, there is a growing interest in using federated technologies to answer more basic questions about decentralized data — like computing counts or rates — that often don’t involve ML at all.
via: Google AI Blog
