Data is key factor to improve performance of our machine learning model. But we know that the data, our model encounters some times have tagged as sensitive data. So it is not a best practice to upload all the users data into server and train it. It leads to the destruction of user's privacy.
But thanks to federated learning , a secure way of training our model within the user device. In this user data is collected and set training environment of the model within the user's device , and the trained results are sent to the server and then encrypted ,making it more secure without leaving the traces of the data it is trained. Generally group of devices are selected to perform training. You may get a doubt of disturbing performance of the device .. ah ..! but these tasks are generally performed when the device is in charging or some time at rest.
image credits : tensorflow medium page
Now another set of devices test the models that are trained on selected set of devices. When we confirm that this model is working fine , then we can release the model to every other device. You can observe federated learning in google products right from gmail to gboard.
I think girls will be more thankful, because it saved them from typing hmm always 😁.
Federated learning have much advantages like protects user's privacy , Decentralization of data , Efficient performance as the model is trained on the real time data.
But making it really working needs huge efforts..
Sunday, June 30, 2019
Artificial intelligence
0 Response to Federated Learning - Secure way of training from real time data.
Comments are personally moderated by our team. Promotions are not encouraged.
Post a Comment