What is Federated Learning?

Standard machine learning approaches require centralizing training data into a common store, but what if we could train ML models on decentralized data? In this episode of AI Adventures, we speak to what federated learning is and how this type of decentralized learning allows machine learning models to have a lower latency, be smarter, and consume less power, while ensuring user privacy. Watch to learn how federated learning can help you train your ML models!

Chapters:
0:00 - Intro
0:55 - Solutions for decentralizing data
2:05 - What is Federated Learning?
3:54 - Secure Aggregation
4:48 - Conclusion

Product: AIML; fullname: Priyanka Vergadia;

#AIAdventures

[LeftLib]

How could I not like a video presented with such enthusiasm? It is an excellent idea as well.

[lawanabdullahiyusuf]

This piece is actually great, thank you Priyanka. Where and how do I start my federated learning journey please?

[vidyutawasthi]

You should also try voice modelling. Your voice and way of speaking is really

[michaeldausmann]

good video. re: secure aggregation. why do you bother with the 'buddy' system? wouldn't this work if each individual phone is sent and uses random values to secure it's data in trasit? what does the buddy thing add?

[haneulkim]

First of all, thanks for an amazing video! I want to ask three questions to clarify my understanding:
1. You've said for model to be distributed user need to be suitable available, if not at the time would it wait until user becomes suitable available(go home at night and charge) then distribute model for training? or if at the time of typing(in our ex case) if user's device is not suitable available they can't learn at all?

2. @3:04 you said only updated model's weights, biases and other parameter leaves the model not the model itself. But right after you are saying "server gets locally trained models". Could you clarify?

3. You said near the beginning that benefit of federated learning is to improve UX by not Giving/Getting data to and from server because internet connectivity, network latency, and others can affect giving/getting data. However we get model from server then pass changed weights and biases to the server and this process is repeated, I'm not sure why giving/getting model from server doesn't face bottlenecks I've mentioned.

[biniltomjose]

I have started my research on federated learning, it's really cool@

[lamarmc]

That was comprehensive due to your style of instruction. Thanks!

[sanjeevkumardwivedi]

very good morning mam,
your explanation is very nice. mam, can we use federated learning on the internet of vehicles environment?
can you suggest few use cases of this learning for vehicles?

[studytimewithjency]

thank u, lots of love from Bangladesh

[emc]

That is freaking well explained, thank you!

[sushmahebbalakar]

Thank you for such am informative video. Easy to understand with such a simple words and great explanation.

[AmitSingh-hzgt]

Keyword here seems like other parameters learned by the model. Weights and biases in themselves are okay, but without the features associated with them would be useless? What's returned would need to be studied too by somebody.

How is data privacy being ensured?

[guillaumeblaquiere]

Very well explained!! But, how to monitor the model performances, be sure that there is no bias, ... Because you haven't data and thus a test dataset!

[jacksibrizzi]

Doesn't this approach create a "bias bubble" around all the clients in the learning process? I think it does. If you acquire your information through this process you will be just like everyone else. Now you don't have to worry about being different.

[IBMSystemsEngineer]

Hearing google metion "eliminating biases" is truly an oxymoron. Extreme Bias is one of their pillars..

[winhwanglim]

Hi, may I check can I use this to work like weglot for my website?

[markrusso]

Great Video. Is it possible to train a pre-trained image recognition model on mobile device. I dont really need it to be federated but just to be trained and used on an ios and android for use on that device. However it would be nice if it was federated learning but dont really need it for my current use case. Any advice would be great. Newbie to ML

[chandravamsi]

If the model needs to trained in a client it needs tensorflow or flower or at least the python framework to train. But the python framework is not installed (is it installed by Android itself by default when the rom is built??)

[krupatk]

well ! thanks for a great explaination. that was an amazing concept. looking forward for future advancements in federated learning. i would also like to do a contribution.

[MahmoudSabry-wrim]

Is the concept of federated learning the same as swarm learning?