# 注意力机制

Posted by Masutangu on September 12, 2022

# 查询、键和值 Query & Key-Value

An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is computed as a weighted sum of the values, where the weight assigned to each value is computed by a compatibility function of the query with the corresponding key.

# 注意力汇聚

## 非参数注意力汇聚

$f(x) = \sum_{i=1}^n \frac{K(x - x_i)}{\sum_{j=1}^n K(x - x_j)} y_i$

\begin{aligned} f(x) &=\sum_{i=1}^n \alpha(x, x_i) y_i\\ &= \sum_{i=1}^n \frac{\exp\left(-\frac{1}{2}(x - x_i)^2\right)}{\sum_{j=1}^n \exp\left(-\frac{1}{2}(x - x_j)^2\right)} y_i \\&= \sum_{i=1}^n \mathrm{softmax}\left(-\frac{1}{2}(x - x_i)^2\right) y_i. \end{aligned}

## 带参数注意力汇聚

\begin{aligned}f(x) &= \sum_{i=1}^n \alpha(x, x_i) y_i \\&= \sum_{i=1}^n \frac{\exp\left(-\frac{1}{2}((x - x_i)w)^2\right)}{\sum_{j=1}^n \exp\left(-\frac{1}{2}((x - x_j)w)^2\right)} y_i \\&= \sum_{i=1}^n \mathrm{softmax}\left(-\frac{1}{2}((x - x_i)w)^2\right) y_i.\end{aligned}

# 注意力评分函数

## 加性注意力

$a(\mathbf q, \mathbf k) = \mathbf w_v^\top \text{tanh}(\mathbf W_q\mathbf q + \mathbf W_k \mathbf k) \in \mathbb{R}$

## 缩放点积注意力

$a(\mathbf q, \mathbf k) = \mathbf{q}^\top \mathbf{k} /\sqrt{d}$

$\mathrm{softmax}\left(\frac{\mathbf Q \mathbf K^\top }{\sqrt{d}}\right) \mathbf V \in \mathbb{R}^{n\times v}$