In the world of big data and artificial intelligence, federated learning is a very attractive way of enabling data sharing in a privacy preserving manner. Clients in a federated learning network never access data from other clients directly and they model parameters they receive are formed from data aggregates. However, under certain conditions the models can memorise information and so there has been much interest in the development of privacy protecting, trustworthy federated learning.
The implementation of such schemes is particularly challenging when one considers the use of federated learning across IoT networks where devices are resource constrained (memory, computational power, battery life). This project aims to explore the implementation of lightweight, privacy preserving federate learning on IoT networks.