Has anybody tried applying this to a blockchain by having the PoW be improvements to models in previous blocks or something? This seems like such an obvious idea (especially with all the hype around blockchain nowadays) that either this exists or I'm missing something crucial about the technique.
Federated Learning
11–13 of 13 posts
Re: Federated Learning
#12TL;DR : Compute the gradient of the error on the user's device and ship that to a server-side centralized model to update its weights. It's a very cool idea that has a lot of interesting applications (among which: learning large statistical user behaviors without "spying" on them). However, there is an unspoken claim that the gradient update doesn't carry enough information about the user data to reconstruct any of i…
If you wanted to take user privacy super seriously, I wonder how feasible it would be to set up a TOR style network to allow users to pass their update back to your server? That way, you don't know who each update came from, and if you isolated each update, you wouldn't even know if two updates came from the same user. I haven't taken much time to consider the ramifications, my gut says this would open you up to mali…
In practise, end-users will probably not setup a TOR(-style) network themselves. That means you'll need to do it for them, so they still have to trust you. At that point, just not storing their IP address is probably easier.
There are still advantages to the TOR-style solution (you wouldn't have the ability to track users without resorting to backdooring), but the slowdown and extra complexity is probably not worth it in most situations.
Re: Federated Learning
#13Has anybody tried applying this to a blockchain by having the PoW be improvements to models in previous blocks or something? This seems like such an obvious idea (especially with all the hype around blockchain nowadays) that either this exists or I'm missing something crucial about the technique.
definitely has been done before.