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

Machine Unlearning Challenge

ai.googleblog.com

Post reply on HN
Print view View original

21–30 of 33 posts

Re: Machine Unlearning Challenge

#21

Post by __loam »

bitcurious wrote: post #12
B1FF_PSUVM wrote: post #10

Earlier quoted context omitted.

> I've heard than some mental illness (maybe schizophrenia) is theorized to be in part due to an inability to forget things. My totally amateur pet theory is that paranoia is threat pattern recognition gone bonkers. Actually, most of what we do with brains is pattern recognition, and if there isn't enough good input they will make shit up.

> My totally amateur pet theory is that paranoia is threat pattern recognition gone bonkers. Supposedly OCD is your brain’s cause-effect loop being too potent. As in, you have a random fear I.e. “stove is on, fire will burn down house,” you go to check the stove, and the act of checking (regardless of its being on) creates the feeling that you saved your house from burning down, so now you feel compelled to check eve…

I have OCD. This is basically accurate in that it's an anxiety disorder that affects your ability to judge whether a worst case scenario is likely or not, but the thoughts are more like "What if I drive across the median and kill a family of 5 in a minivan" or "What if I pull my genitals out in this meeting and try to fuck my boss". The compulsions are usually not as logically coherent as needing to check if the stove is on or the house will burn down (though there are people who experience ocd like this). Usually my compulsions happen as a way to try and stop thinking those thoughts, like pulling over and playing internet chess for half an hour. The problem is that the compulsions steal a lot of time and don't typically address the underlying obsessive thought.

Re: Machine Unlearning Challenge

#22

Post by kxcrossing »

__loam wrote: post #19
dleeftink wrote: post #18

As with many ML-phrases, the use of 'unlearning' frames data modelling as a false dichotomy between 'learnable' and 'forgettable' data. Whereas humans are able to forget over time, it would be quite disturbing to block some memories from access entirely, how traumatic they might be (and quite apparent among people suffering memory loss). While from a privacy perspective, not all 'data points' (i.e. memories) need be…

It's just statistics guys. You either put the data in the training set or you don't.

Well, isn't this challenge about altering a model after-the-fact? I.e. we are stuck with this data in the training set and must figure out a way to clean up the model

Re: Machine Unlearning Challenge

#24

Post by vintermann »

buildbot wrote: post #2

While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.

I always though it funny that in short term, LMMs are (or can be) much better at forgetting than humans can. If a person tells you, "I'm going to forget you ever said that", you know they won't actually forget. An LMM, on the other hand, can just drop the context, and they're literally going to forget it ever happened. They already train chatbot agents with a special "end the conversation" token, it would be easy to train them with a "drop the context" token too.

Re: Machine Unlearning Challenge

#25

Post by inglor_cz »

version_five wrote: post #3
buildbot wrote: post #2

While this post seems aimed more at compliance or sensitive data issues, “unlearning” aka forgetting itself may be essential for better or more human like AI agents. You are as much defined by what you have forgotten as what you have learned.

I've heard than some mental illness (maybe schizophrenia) is theorized to be in part due to an inability to forget things. Certainly normal human existence involves preferential remembering and forgetting. For example not dwelling on pain or failure etc. Gradient descent obviously has none of that, it has not feelings or goals, and so there would be no preferential remembering or forgetting other than to do better ne…

In 1999 I dated a girl whose father was a military doctor. He was the only person whom I ever knew to have an almost total recall. Like, you asked him what happened on this particular day five years before, and he told you exactly what. If there were records (like photos), they would match his words.

He was also quite unassuming and very "normal". No trace of mental dysbalance.

Re: Machine Unlearning Challenge

#27

Post by weare138 »

Is there like a cash prize for solving a major problem with one of Google products? It seems disingenuous for Google to frame this as some academic challenge when it's clearly for Bard, Google's commercial product.

Re: Machine Unlearning Challenge

#28

Post by iandanforth »

I'll drop my idea here since I won't be participating. Trade disk for privacy. Basically you keep all your initialized weights, gradient updates from the training run and an index of what samples appeared in what batches. Then when you need to delete a sample, you find all the batches containing the target, reconstitute batches without that sample, and save those updated batches. You then take the initial weights and apply all the gradients that didn't come from contaminated batches. Finally you run a small additional bit of training with the cleaned batches.

This idea doesn't fully remove the influence of the target data (any previously saved gradient update from after a contaminated batch contains some information about the state of the network prior to update) but it may be a sufficient and efficient way to quickly reconstitute a network with far less influence from the problematic data.

Just an idea and I haven't tried it, so maybe it's bunk, but there you are!

Re: Machine Unlearning Challenge

#29

Post by incone123 »

ChatGTP wrote: post #17
gojomo wrote: post #8

Joel: "Is there any risk of brain damage?" Dr. Mierzwiak: "Well, technically speaking, the operation is brain damage, but it's on a par with a night of heavy drinking. Nothing you'll miss." - Eternal Sunshine of the Spotless Mind (2004)

None of this is true for those who abstain from Alcohol :)

Did you miss the clause 'on a par with'?

Re: Machine Unlearning Challenge

#30

Post by Filligree »

iandanforth wrote: post #28

I'll drop my idea here since I won't be participating. Trade disk for privacy. Basically you keep all your initialized weights, gradient updates from the training run and an index of what samples appeared in what batches. Then when you need to delete a sample, you find all the batches containing the target, reconstitute batches without that sample, and save those updated batches. You then take the initial weights and…

Did you do any estimate of how much storage is required?

On the face of it, I would expect the gradients to take about as much space as the weights. So you’d be checkpointing your network at every batch, in effect.

Post reply on HN