1

I just started studying federated learning and want to apply it to a certain dataset, and there are some questions that have risen up.

My data is containing records of 3 categories, each of which is having 3 departments. I am planning to have 3 different federated learning models for each category and treat the three department of this category as the distributed clients.

Is this possible? or building federated learning models requires having thousands of clients?

Thanks

Eden
  • 325
  • 3
  • 13
  • Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. – Community Feb 03 '22 at 10:47

1 Answers1

0

Difficult to say by what you have provided in your question. Usually, when building a federated learning system, you are extending your centralized approach to one with data split/partitioned between segregated clients. Again, depending on the type of data you have, the type of task you are trying to solve and also the amount of data required to solve the task in a centralized approach, these factors along with other ones will depend how many clients you can use and how much data is required at each client. Additionally, the aggregation method that you wish to use combine the parameters from different clients will affect this. I suggest experimenting with different client numbers and partitioning methods and seeing what suits your needs.

Daniel Al Mouiee
  • 1,111
  • 8
  • 11
  • 1
    That's right, I was experimenting the data on traditional ML models to see how it works. I also want to ask about the data type used in TFF, all of the tutorials available online are for image datasets, I have a dataset containing students records as numerical data, so If you can tell me if it is possible to work on with numerical data in TFF? – Eden Feb 15 '22 at 21:02
  • I'd imagine that it is possible to build a federated learning system using numbers as input. If you are considering a regression problem for federated learning then there are a number of publications on this. As for TFF particularly, I'm not familiar with it I've been using a tool called Flwr with python and I know it is possible with it. So I'd imagine it shouldn't be too difficult for TFF, consider looking through it's api documentation if you are set on using TensorFlow for federated learning. – Daniel Al Mouiee Feb 15 '22 at 21:17
  • Thanks for your reply, it is mainly a classification problem, if you can suggest me any paper to start with I would be really appreciated. – Eden Feb 16 '22 at 11:53