A SURVEY ON CHALLENGES OF FEDERATED LEARNING

Abstract

Federated Learning is a new paradigm of Machine Learning. The main idea behind FL is to provide a decentralized approach to Machine Learning. Traditional ML algorithms are trained in servers with data collected by clients, but data privacy is the primary concern. This is where FL comes into play: all clients train their model locally and then share it with a global model in the server and receive it back. However, FL has problems, such as possible cyberattacks, aggregating most appropriately, scaling the non-IID data, etc. This paper highlights current attacks, defenses, pros and cons of aggregating methods, and types of non-IID data based on publications in this field.