Distributed differential privacy for federated learning

Posted by Florian Hartmann, Software Engineer, and Peter Kairouz, Research Scientist, Google Research

Federated learning is a distributed way of training machine learning (ML) models where data is locally processed and only focused model updates and metrics that are intended for immediate aggregation are shared with a server that orchestrates training. This allows the training of models on locally available signals without exposing raw data to servers, increasing user privacy. In 2021, we announced that we are using federated learning …

aggregation android data differential privacy distributed engineer feature federated learning google google research machine machine learning metrics neural networks on-device learning privacy research server servers smart software software engineer text training updates