Huge increase in edge devices over the world with powerful processors inspired many researchers to apply decentralized machine learning techniques so that these edge devices can contribute to train deep neural networks. Among those decentralized machine learning schemes, federated learning has gained tremendous sympathy as it grants privacy to the edge devices as well as diminishing communication costs. Having presented well performance in both unbalanced and massively distributed data, the results for federated learning are promising, thus it paves the way for many opportunities in various applications such as:

• Vehicular networks
• Augmented reality based demonstration in museums or online games etc.
• Drone networks
• Smart cities