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

11–20 of 77 posts

Re: Federated Learning

#11

Post by carlosdp »

arkades wrote: post #5

call me jaded but: If you’re paying for PR firms to produce cartoons about how good you are for privacy, you’re probably terrible for privacy. This feels like Google’s Joe Camel moment.

It wasn't a PR firm, it was this cartoonist: https://lucybellwood.com/

I mean, the comic addresses the fact the current model is bad for privacy right out of the gate and then shows how this team is trying to solve it, what more do we want from them?

Re: Federated Learning

#12

Post by carlosdp »

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?

It could always end up being just fluff, but given it's an active research area and they've open sourced a framework based on the concept already, plus the fact the model is cost-advantageous given you get to offload training to a fleet of customer devices instead of paying for your own servers, it could be the real deal.

I started reading it looking at it from a cynical view, but ended it with a "hmm... this could actually work," especially after reading about Secure Aggregation. That's badass.

Re: Federated Learning

#13

Post by patrickthebold »

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.

Re: Federated Learning

#14

Post by carlosdp »

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.

Sure, it doesn't address that problem head on, however if they moved most stuff to a federated model, they're only a hop, skip, and a jump away from doing ad-selection on-device too, right? I think that if the model proves successful, it could end up proving out the concept enough to incentivize at least trying it out.

Re: Federated Learning

#15

Post by Thorrez »

arkades wrote: post #5

call me jaded but: If you’re paying for PR firms to produce cartoons about how good you are for privacy, you’re probably terrible for privacy. This feels like Google’s Joe Camel moment.

Google Chrome launched with a comic by Scott McCloud in 2008. It looks like Scott McCloud helped on this Federated Learning comic as well.

https://www.google.com/googlebooks/chrome/big_00.html

Re: Federated Learning

#17

Post by wybiral »

How do they assure you that the training algorithm isn't just exfiltrating your data?

Edit: By that I mean... What's stopping the model from being as simple as "learn my personal information"?

Re: Federated Learning

#18

Post by cavisne »

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?

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 prevent FB and AMZN from storing your raw data

4) Profit

That said theres nothing stopping FB doing federated learning within their app on mobile, I just don't think they have the privacy background to bother.

Re: Federated Learning

#19

Post by pas »

wybiral wrote: post #17

How do they assure you that the training algorithm isn't just exfiltrating your data? Edit: By that I mean... What's stopping the model from being as simple as "learn my personal information"?

Nothing, of course. But they are probably going to use an open source implementation with probably some kind of deterministic build/compile systems, so they can show you what the training algorithm is (that it does not contain a hidden user id or such to magically "overfit" for that user), and similarly the training questions should also be knowable and provably non-user-specific.
Post reply on HN