Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Federated Learning

federated.withgoogle.com

Post reply on HN
Print view View original

71–77 of 77 posts

Re: Federated Learning

#71

Post by hatsunearu »

defen wrote: post #56
cavisne wrote: post #18

Earlier quoted context omitted.

Well the cynical view would be. 1) This still lets you have personalized models, just trained on more than 1 user, thats fine at google's scale anyway 2) Their competitors (FB, AMZN) dont have the edge compute (Android) to do this, and to a lesser degree don't have the ML stack (however Android implements this at the API level will be very Tensorflow focused) 3) Now google can push for privacy regulations that preven…

> Their competitors (FB, AMZN) dont have the edge compute (Android) to do this It's not Android scale but Amazon has sold 100 million Alexas.

Doubt Alexas have enough juice to do on device training...

Re: Federated Learning

#72

Post by ddtaylor »

CyanTas wrote: post #58
arthurcolle wrote: post #41

Earlier quoted context omitted.

Does this actually work today? I was tangentially involved in some 'zero protocol'/zcash-related projects a few years back and the lack of ability to communicate and transfer information while being able to perform computation on it was a major drawback to most of the interesting ideas in the space. Are they actually using this in this intended federated learning plan? If so that's a truly major innovation.

Fully homomorphic encryption, in which you can do arbitrary computation on encrypted data, is still quite slow. But partially homomorphic decryption, in which you can add encrypted values together but not multiply (or vice versa), is quite efficient. And since the secure aggregation protocol only needs to add together encrypted values to get an average, it only needs partially homomorphic encryption properties.

I believe there is also a proof that says any partially homomorphic system can be reworked into a FHE.

Re: Federated Learning

#73

Post by jhanschoo »

grantlmiller wrote: post #6

First, I've loved that Google open sourced Tensor Flow Federated as a way to encourage the rest of the world to adopt this method of decentralized machine learning. Second, I was a bit disheartened that this concept had to be explained with a comic strip to make it accessible because I hoped the benefits were clear to everyone. Third, I read the comic strip, learned new things (secure aggregation protocol, wtf, amazi…

The comic strip format helps in that the audience is not just potential developers, but also the general privacy-conscious consumer.

Re: Federated Learning

#74

Post by CyanTas »

ddtaylor wrote: post #72
CyanTas wrote: post #58

Earlier quoted context omitted.

Fully homomorphic encryption, in which you can do arbitrary computation on encrypted data, is still quite slow. But partially homomorphic decryption, in which you can add encrypted values together but not multiply (or vice versa), is quite efficient. And since the secure aggregation protocol only needs to add together encrypted values to get an average, it only needs partially homomorphic encryption properties.

I believe there is also a proof that says any partially homomorphic system can be reworked into a FHE.

You're thinking of "somewhat homomorphic encryption", which is homomorphic encryption that can support both addition/OR and multiplication/AND, but only in circuits of a limited depth. The original FHE paper did indeed prove that you can rework any "somewhat homomorphic" system into a fully homomorphic one.

Partially homomorphic encryption is different because it really only enables one of those two types of operations. For example, Pallier encryption has the property that Enc(A) + Enc(B) = Enc(A+B), but there's no way to go from Enc(A) and Enc(B) to Enc(A×B).

Re: Federated Learning

#75

Post by jameslevy »

patrickthebold wrote: post #13
ahelwer wrote: post #2

All right, I'm cynical as all heck about ad companies and privacy, but this has me optimistic. Somebody disillusion me, why shouldn't I be optimistic?

Looks like everyone gets the same model. So it won't be used for things like targeted ads. Cynical view is that it's only used when Google doesn't want your individual data. This will help muddy the waters in discussions about privacy.

Just because everyone gets the same model doesn't mean you can't have targeted ads. It just means the prediction model isn't modeled specific to your behavior. It can still make personalized predictions based on your search input, email content, etc.

Re: Federated Learning

#76

Post by capitalsigma »

krick wrote: post #46
capitalsigma wrote: post #35

Earlier quoted context omitted.

It's legitimate to call the aggregate data that the central server has "non-private." For example, it's ok to publish how many thousands of cars drive on a particular highway -- that's public data. It's not ok (broadly) to publish what route John Doe drives to work everyday -- that's private data.

Absolutely not. Actually, I kind of reflected it in my concerns: it makes it easier for somebody who wants to push such a polemic (as yourself) to do so, but by no means it is universally true. I mean, it might be, if everything that your model learns is the number of cars on a highway. But there's absolutely no reason to assume it is. It might as well learn anything else about your private life. You might be tempted…

I believe that what I described above is actually the way that private data is defined today: for each sufficiently large data set, there exists a K such that K-anonymity means the data is public.

If you find it concerning that it's possible to predict behavior based on demographics, I don't know what to tell you. Do you think that psychology studies are an invasion of privacy?

Re: Federated Learning

#77

Post by ddtaylor »

CyanTas wrote: post #74
ddtaylor wrote: post #72

Earlier quoted context omitted.

I believe there is also a proof that says any partially homomorphic system can be reworked into a FHE.

You're thinking of "somewhat homomorphic encryption", which is homomorphic encryption that can support both addition/OR and multiplication/AND, but only in circuits of a limited depth. The original FHE paper did indeed prove that you can rework any "somewhat homomorphic" system into a fully homomorphic one. Partially homomorphic encryption is different because it really only enables one of those two types of operatio…

Thanks for the clarification.
Post reply on HN