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

Differential Transformer

arxiv.org

Post reply on HN
Print view View original

161–170 of 188 posts

Re: Differential Transformer

#161

Post by vessenes »

f38zf5vdt wrote: post #155
vessenes wrote: post #140

Earlier quoted context omitted.

Yes. This looks really, really good to me. Cross the board improvements in training time, perplexity improvements per both token trained and per model size. I'm reminded of MoE architectures, in that world we're choosing an optimal small model to process part or all of the inference job; I wonder if MoE got some of the same benefits from forcing the Transformer to distinguish between alternate possibilities. In any e…

There is a downside, every attention layer has to effectively compute attention twice (run scaled_dot_product_attention). As scaled_dot_product_attention is usually one of the most expensive operations in training and inference of a model, it seems like networks using this may be substantially slow and perhaps should considered against larger networks with more attention layers. https://github.com/microsoft/unilm/blo…

Interesting. This is one of those areas where edge inference needs might be different than data center: to get an 11b quality model in 7b at the cost of 30% more inference time is probably a full yes for anyone doing local inference. And let’s remember that memory bandwidth is a huge factor as well; 30% smaller equals 30% boost in memory based time costs. Anyway I’m interested in trying this out.

I wonder if the specific setup might be extra effective for coding tuned models as well - you get one coding transformer and one ‘bad habits/chat/other non coding stuff’ negative transformer.

Re: Differential Transformer

#162

Post by Grosvenor »

Grosvenor wrote: post #152
impossiblefork wrote: post #150

Earlier quoted context omitted.

I've tried that in a small transformer that I trained from scratch and it didn't really make any difference. I also made a version where I made this trainable somehow, probably by replacing the 1 with a constant associated with the layer, and that didn't make any difference either. I didn't follow Miller's proposal quite as he wrote it though and I put the mechanism in all the layers rather than avoiding it at the en…

I guess the next step is to see if you're getting those mega activations as he describes. A/B test the two models and compare? Would be interesting to see if these activations only show up on larger models, or they're some relation to model size.

https://news.ycombinator.com/item?id=36871528

Hah. Yes. It looks like they only show up in models with 6.7B parameters or more.

The problem can start at 125M. Small enough to test on a whim.

So train a model that exhibits these behaviours, then try it out.

Re: Differential Transformer

#164

Post by brrrrrm »

Grosvenor wrote: post #139
Imnimo wrote: post #108

I feel like I'm missing a key insight here. I understand the problem that regular softmax attention struggles to approach assigning zero attention to irrelevant stuff. And I get that having this subtraction formula makes it possible to assign exactly (or near) zero attention weight without having crazy outlier activations. But it seems like it also makes it very easy to have negative attention weight (which is equiva…

Regular softmax (and attention) has an error in it. softmax should be exp()/1+∑exp() Notice the 1 added to the denominator. The difference is at the negative limit, softmax can be 0, instead of some epsilon. The same could be done by adding an extra zero value in x. Downside is, you have to retrain your model from scratch to fix this.

that silly softmax1 blog post is not worth the read. no one uses it in practice

if you think about it, the "escape hatch" is the design of the entire transformer dictionary. if Key/Query attention misaligns with Value's weights, you get a layer head that does not attend to anything...

Re: Differential Transformer

#165

Post by magicalhippo »

testdfkjahdfh wrote: post #131
magicalhippo wrote: post #79

Earlier quoted context omitted.

An interesting aspect is that they don't do a plain subtraction, but rather subtract a portion of the second softmax. This makes sense, if one considers that the two copies are identical then the softmax outputs would be identical and the difference is zero everywhere. However, by subtracting a scaled copy, the normalization of the difference seems to really boost the signal value(s) over the "noise", making the sign…

if two attentions A, B are identical, would (A - lambda * B) be just (1-lambda) * A, how does it "boost the signal value(s) over the "noise""?

How embarrassing, I had one of those "autocorrect moments". I somehow put the lambda inside the softmax when thinking and trying it without realizing. So what I was playing with in a spreadsheet (so not so obvious as plain code) was

    softmax(A) - softmax(lambda * A)
And as so happens, normalizing the output of that that with my test vectors seems to really boost the output the largest component if A and B are equal.

Re: Differential Transformer

#166

Post by theGnuMe »

phire wrote: post #65
msoad wrote: post #7

Like most things in this new world of Machine Learning, I'm really confused why this works? The analogy to noise-cancelling headphones is helpful but in that case we clearly know which is signal and which is noise. Here, if we knew why would we even bother to the noise-cancelling work?

Noise cancelling headphones are probably the wrong analogy here. The better example is the differential signalling used in professional audio and many digital signaling protocols like Ethernet, HDMI and USB. Instead of using one wire, referencing to ground, they send the signal as the difference between both wires. Both wires end up carrying the same signal with inverted polarity. Because both wires are running next…

This is a cool idea!

Re: Differential Transformer

#168

Post by espadrine »

smallnamespace wrote: post #153
espadrine wrote: post #113

Earlier quoted context omitted.

It is a neat approach, but one that comes with a tradeoff, IIUC: doubling the key heads. I wonder if a different approach without that issue exists. For instance, using max(0, exp(x)-1) instead of exp(x) in the softmax attention formula. That way when the query is orthogonal to the key (or worse), it does not contribute.

> using max(0, exp(x)-1) instead of exp(x) Won't this cause the gradient to vanish on the left half, causing problems with training?

That is a concern that is shared with ReLU. But since the weights are shared across the context/minibatch, perhaps that would not be an issue, similar to ReLU.

Re: Differential Transformer

#170

Post by radarsat1 »

dartos wrote: post #70
patcon wrote: post #34

I wonder what is lost here. Surely there's a trade-off... I'm wondering if there's any effect of "creativity", or ability to interpolate between concepts. Hallucination and creativity feel very related to me. I understand hallucinating as simply being misaligned with the space humans feel appropriate to interpolate between

> Hallucination and creativity feel very related to me. Why? I see them as just sampling errors. Sure a mistake can spark inspiration sometimes, but creativity is much more than mistakes. > I understand hallucinating as simply being misaligned with the space humans feel appropriate to interpolate between These language models are next-token predictors. The way the next token is predicted is by sampling a probability…

Often see this argument but it doesn't hold water for me. What we call hallucination is usually when the model says something confidently wrong. Yes the sampling procedure is nondeterministic but this is unrelated to hallucinations. The model can generate a distribution to sample with very little weight on the "wrong" output and then this should be ignored by procedures like top-k sampling. The fact that this doesn't easily solve the problem shows that hallucination is a deeper problem in the model itself and not just a byproduct of sampling.
Post reply on HN