The last few years have been strongly marked by artificial intelligence, machine learning, and telecommunications networks. As a result, several challenges arose in data science regarding how data can be accessed and stored. For example, sharing of telecommunication network data, for example, even at high aggregation levels, is highly restricted nowadays due to privacy legislation and regulations and other critical ethical concerns. It leads to scattering data across institutions, regions, and states, inhibiting the usage of AI methods that could otherwise take advantage of data at scale.

This webinar aims to present the basic definitions of federated learning, categorizations regarding data partition, privacy, network topology, and data availability. We will also discuss the proposed approach to building the bridge between federated learning and data streams in the context of the AIDA project.