Seconding this, the terms "Query" and "Value" are largely arbitrary and meaningless in practice, look at how to implement this in PyTorch and you'll see these are just weight matrices that implement a projection of sorts, and self-attention is always just self_attention(x, x, x) or self_attention(x, x, y) in some cases, where x and y are are outputs from previous layers.

Plus with different forms of attention, e.g. merged attention, and the research into why / how attention mechanisms might actually be working, the whole "they are motivated by key-value stores" thing starts to look really bogus. Really it is that the attention layer allows for modeling correlations and/or multiplicative interactions among a dimension-reduced representation.

▲

tayo42 an hour ago | parent | next [-]

>the terms "Query" and "Value" are largely arbitrary and meaningless in practice

This is the most confusing thing about it imo. Those words all mean something but they're just more matrix multiplications. Nothing was being searched for.

	▲	D-Machine 29 minutes ago \| parent [-]
		Better resources will note the terms are just historical and not really relevant anymore, and just remain a naming convention for self-attention formulas. IMO it is harmful to learning and good pedagogy to say they are anything more than this, especially as we better understand the real thing they are doing is approximating feature-feature correlations / similarity matrices, or perhaps even more generally, just allow for multiplicative interactions (https://openreview.net/forum?id=rylnK6VtDH).

▲

profsummergig 8 hours ago | parent | prev [-]

Do you think the dimension reduction is necessary? Or is it just practical (due to current hardware scarcity)?

	▲	D-Machine 40 minutes ago \| parent [-]
		Definitely mostly just a practical thing IMO, especially with modern attention variants (sparse attention, FlashAttention, linear attention, merged attention etc). Not sure it is even hardware scarcity per se / solely, it would just be really expensive in terms of both memory and FLOPs (and not clearly increase model capacity) to use larger matrices. Also for the specific part where you, in code for encoder-decoder transformers, call the a(x, x, y) function instead of the usual a(x, x, x) attention call (what Alammar calls "encoder-decoder attention" in his diagram just before the "The Decoder Side"), you have different matrix sizes, so dimension reduction is needed to make the matrix multiplications work out nicely too. But in general it is just a compute thing IMO.