What is Federated learning?

Lately, the topic security on machine learning is enjoying increased interest. This can be largely attributed to the success of big data in conjunction with deep learning and the urge for creating and processing over larger data sets for data mining. Since the machine learning is becoming a part of the day today life, making use of our data, special measures must be taken to protect privacy.

In federated learning the model is learned by multiple clients in decentralized fashion. Here learning is shifted to the clients and only the learning parameters are centralized by the trusted curator. This curator the distribute aggregate model back to the client. The approach of federated learning can be vastly used in mobile applications by considering the computational power and the privacy aspects.

When a model is learned in conventional way, its parameters reveal information about the data that was used during training. In order to solve this problem discussion of differential privacy to learning algorithms has being developed. It is to ensure that the learned model does not know a client participate during decentralized training and client’s data set will be protected from other client attacks.

 

Federated learning is an approach which enables us to get rid of such complexities by enabling the models to be trained at the device itself. These trained models are then sent back to a central server where they are aggregated and then one consolidated model is sent back to the devices. In federated learning communication between curator and the client might be limited. The challenge of federated optimization is to learn a model with minimal information over-read between client and the curator, data might be unbalanced and massively distributed. However even nowadays the there are many apps which use federated learning such as language modeling for mobile keyboards and voice recognition, image classification of predicting which photos people will share. The main advantage of federated learning is that client never share data. Only model parameters.

Studying and investigating the contribution of Information technology in a modern field such as Federated learning can be adapted in numerous scenarios in the future. The major problem of digitize users which is misusing unprotected personal data by third parties can be reduced by optimizations of federated learning in regards with machine learning application which use internet. And, the study of optimizing and minimizing the computational power can be reduced by using cloud integrated learning models and neural networks.

Hope you have enjoyed it. Cheers!! :)