Attention Model（注意力模型）思想初探

时间 2019-12-05

标签 attention model 注意力模型思想初探繁體版

原文原文链接

1. Attention model简介

0x1：AM是什么

深度学习里的Attention model其实模拟的是人脑的注意力模型，举个例子来讲，当咱们观赏一幅画时，虽然咱们能够看到整幅画的全貌，可是在咱们深刻仔细地观察时，其实眼睛聚焦的就只有很小的一块，这个时候人的大脑主要关注在这一小块图案上，也就是说这个时候人脑对整幅图的关注并非均衡的，是有必定的权重区分的。这就是深度学习里的Attention Model的核心思想。git

AM刚开始是应用在图像领域里的，而且在图像处理领域取得了很是好的效果，以后，就有人开始研究怎么将AM模型引入到NLP领域。最先提出 attention 思想的是这篇paepr，“Neural machine translation by jointly learning to align and translate”，这篇论文最先提出了Soft Attention Model，并将其应用到了机器翻译领域。github

0x2：AM在机器翻译中的应用

Encoder-Decoder模型算法

Relevant Link:shell

https://blog.csdn.net/mpk_no1/article/details/72862348
https://machinelearningmastery.com/encoder-decoder-attention-sequence-to-sequence-prediction-keras/
https://arxiv.org/pdf/1409.0473.pdf
https://www.zhihu.com/question/36591394

0x3：Attention Mechanism分类

1. hard: Attention和soft: Attention

简单来讲，soft attention是对输入向量的全部维度都计算一个关注权重，根据重要性赋予不一样的权重。api

而hard attention是针对输入向量计算获得一个惟一的肯定权重，例如加权平均。安全

2. Global Attention 和 Local Attention

3. Self Attention

Self Attention与传统的Attention机制很是的不一样：网络

传统的Attention是基于source端和target端的隐变量（hidden state）计算Attention的，获得的结果是源端的每一个词与目标端每一个词之间的依赖关系。app

但Self Attention不一样，它分别在source端和target端进行，仅与source input或者target input自身相关的Self Attention，捕捉source端或target端自身的词与词之间的依赖关系；而后再把source端的获得的self Attention加入到target端获得的Attention中，捕捉source端和target端词与词之间的依赖关系。dom

所以，self Attention Attention比传统的Attention mechanism效果要好，主要缘由之一是：函数

传统的Attention机制忽略了源端或目标端句子中词与词之间的依赖关系，相对比，self Attention能够不只能够获得源端与目标端词与词之间的依赖关系，同时还能够有效获取源端或目标端自身词与词之间的依赖关系，以下图所示。

Relevant Link:

https://zhuanlan.zhihu.com/p/31547842 
https://blog.csdn.net/jteng/article/details/52864401

2. 经过一个简单的例子来理解attention model的思想原理

须要明白的是，AM不是一个具体的算法或者模型，AM更多的是一种思想，笔者以为它实质上是一种更加合理的深度神经网络结构设计思想，以及特征权重调整策略。

0x1：Dense Layer - 在DNN隐层中加入soft attention机制

这个小节，咱们经过一个简单的DNN神经网络里展现AM思想。

如今咱们有一个dim=32维度的输入vector，咱们正在设计一个DNN网络结构，来对这个dim32 vector进行进行分类预测。

在开始写代码以前，咱们经过观察数据的几率分布，发现了一个颇有趣的现象，训练数据对应的特征向量中有一个维度起到了决定性的做用，输入数据以下图

testing_inputs_1 [[-7.03187310e-01  1.00000000e+00 -3.21814330e-01 -1.75507872e+00
   2.06664470e-01 -2.01126457e+00 -5.57250708e-01  3.37217008e-01
   1.54883597e+00 -1.37073656e+00  1.42529140e+00 -2.79463910e-01
  -5.59627907e-01  1.18638337e+00  1.69851891e+00 -1.69122016e+00
  -6.99522844e-01  5.82962842e-01  9.78222630e-01 -1.21737211e+00
  -1.32939545e+00 -1.45474227e-03 -1.31465268e+00 -3.79611743e-01
   1.26521065e+00  1.20667744e-01  1.47941778e-01 -2.75372579e+00
  -3.56896324e-01  7.71783656e-03  1.47827716e+00 -9.57614629e-01]
 [ 1.32900811e+00  0.00000000e+00  4.71557202e-01 -8.74652950e-03
   3.67018689e-01  1.11855474e+00 -8.38993512e-03  4.66315379e-01
   1.26326870e+00 -9.01654654e-01 -1.02884269e+00  5.69678421e-01
   6.41664780e-01  2.59811930e-01  1.19317814e+00 -1.04630036e+00
   1.39888921e-01 -1.73065584e+00 -1.30623116e-01 -1.31026002e+00
  -2.17131242e+00 -1.06618141e+00 -3.31618443e-02  1.46639575e+00
   8.76643096e-01  6.69989580e-01  6.97449511e-01 -2.52785434e-01
   5.67987107e-01  3.04387858e-01 -1.00002960e+00 -2.45641783e+00]
 [ 2.52307022e-01  1.00000000e+00 -1.58345465e+00  1.98042282e-01
   8.52522298e-02  6.40507750e-01 -7.90658155e-01  7.71182395e-01
  -1.95067777e+00 -1.29401021e+00 -1.07352377e+00  3.06910919e-02
   7.74109345e-01 -8.71396303e-01  1.66344014e-01  6.35789777e-01
   1.08167197e+00 -2.82773662e-01  1.55478794e+00 -8.58308135e-01
  -2.79650432e-01 -8.54234325e-02 -2.19597647e-01 -2.17359887e+00
   9.06332427e-01  7.50338575e-01 -5.75259737e-01 -3.68953224e-01
   7.65748246e-01 -1.10066159e+00  7.33829660e-01 -3.15740222e-02]
 [-1.27394186e+00  0.00000000e+00 -5.42515179e-01 -1.05202857e+00
  -7.75720653e-01 -1.23228165e-01 -5.36931271e-01  1.65373406e-01
   8.99855721e-01  1.25719599e+00  1.15406861e+00 -6.74225801e-01
   8.83266671e-01 -1.80074100e+00  3.15524021e-01 -2.98942433e-01
   9.23266706e-01 -8.64610423e-01  9.06323896e-01  1.43665365e-01
  -4.28784038e-01  4.36334858e-02 -1.15963013e+00 -1.44581716e-01
   1.06269721e+00  1.50348168e+00  8.90477309e-01  1.10184730e-01
  -2.80878365e-01  4.70876779e-01 -1.22654812e-01  1.80971612e+00]
 [-2.11504034e-01  0.00000000e+00  5.60009299e-01 -1.17945640e+00
  -4.67803781e-01 -1.74241319e+00 -3.70322401e-03 -2.17006719e+00
   4.24510049e-01  1.46478639e-01  5.92744407e-02 -4.91253927e-01
  -1.01717308e+00  4.19307196e-01 -7.71367508e-01  1.43788652e+00
   2.68676712e+00  3.96732882e-01  4.76923961e-01  8.15901697e-01
  -5.03092218e-01  1.44864196e-01  3.91584490e-02 -6.12835945e-01
   7.00882108e-01  9.76864848e-01 -6.30941522e-01 -8.38602720e-01
  -4.39203663e-01 -1.36452679e+00 -1.27237114e+00  8.60190888e-01]
 [ 9.14860457e-01  1.00000000e+00  1.56077637e-01  1.15855621e+00
  -4.98210125e-01  1.67069107e+00  4.31765280e-01  4.26712047e-01
   9.86745986e-01  9.77680603e-01 -1.06466820e+00  5.38847940e-01
   8.43082569e-01  9.00722906e-01 -8.01677331e-01  4.87130812e-01
  -3.58399587e-01  1.20297675e+00  4.58699197e-01 -1.11963082e+00
   3.35130398e-01 -6.86900220e-01  1.20681682e+00  1.91752106e+00
   5.42198956e-01  7.22353555e-01 -1.74881350e-01 -1.15996824e-01
  -1.98712683e+00  9.98292115e-03  7.12149198e-02 -1.75004126e+00]
 [ 5.54438377e-01  0.00000000e+00  1.72070508e+00 -2.39421276e+00
  -4.38335835e-01  1.22198125e+00  3.74376988e-01 -1.38100426e+00
  -6.76686553e-01  4.07591917e-01  5.93619771e-01  7.83618421e-01
   6.73002113e-01  4.78781433e-01  8.39040116e-01  8.69123716e-01
   1.34632773e+00  1.36734769e+00  3.66827392e-01  3.60041568e-01
   6.66945023e-01 -1.14536483e+00  4.38891453e-01 -4.37844713e-01
  -4.65689776e-01  3.12033012e-02 -8.19522312e-01  7.58853868e-01
   5.18056531e-01  4.28196906e-01  2.08135008e-01  1.24826488e+00]
 [ 1.04258559e+00  0.00000000e+00 -5.93238790e-01  1.52406418e+00
   1.21646035e+00  1.05836917e+00 -5.16890856e-01  1.08085391e+00
  -1.38284038e+00  1.06456352e-01  2.74257861e-01 -1.63748280e+00
   9.94120958e-01 -1.36070702e+00 -3.46128572e-01  1.56069434e+00
   6.36408438e-01 -2.13655632e-01 -5.30028711e-01 -1.14739552e+00
  -1.33102035e+00  8.67112945e-01  1.01777222e-01 -5.65421800e-01
   5.44866549e-01 -5.88216752e-01 -1.53028975e+00 -1.05510083e+00
   1.23102591e+00  1.49268412e+00  1.09572693e+00 -8.32754259e-01]
 [ 1.42119684e+00  1.00000000e+00 -6.68588743e-01  2.06587470e+00
   6.73939981e-01  1.78367879e-01  1.20959596e+00  2.05228057e+00
   1.17298340e+00 -2.99209254e-01  1.54491060e+00  5.13288354e-01
  -4.70304173e-01 -3.10097090e-01 -4.28043935e-01 -1.40723789e+00
  -7.96590363e-01 -8.85643489e-01  2.11063371e+00  1.07039253e+00
   1.39945292e+00  5.71403123e-01  2.75430532e-01 -1.99253003e-01
  -3.59019207e-01  1.26609682e-01 -1.69233428e+00  1.33714780e+00
  -1.10716769e+00 -5.72247993e-01  8.97152528e-01 -1.28169975e+00]
 [-1.89902418e+00  0.00000000e+00 -2.82853143e-01 -4.48757897e-01
   1.14923027e+00 -9.81086421e-01 -1.43486014e+00 -7.53626739e-01
   1.37505923e+00  6.51163018e-03 -5.37901188e-01  4.93670710e-01
  -8.27477300e-01  2.21030844e-01 -5.26978585e-01 -4.00566932e-01
  -4.59691412e-01 -1.87982990e+00  5.19494331e-01 -1.77753816e+00
  -2.89858663e-01  3.67898297e-01  9.63175026e-01 -4.51156518e-01
  -1.43890933e-01 -6.47600423e-01  7.69697009e-01 -1.29930416e+00
   7.55207368e-01  1.29158295e-01  1.12152724e+00 -3.52497951e-01]]
testing_outputs [[1]
 [0]
 [1]
 [0]
 [0]
 [1]
 [0]
 [0]
 [1]
 [0]]

从图中能够看到：

1. A vector v of 32 values as input to the model (simple feedforward neural network).
2. v[1] = target.
3. Target is binary (either 0 or 1).
4. All the other values of the vector v (v[0] and v[2:32]) are purely random and do not contribute to the target.

按照rule-based或者决策树的思想，仅仅根据特征进行判断，就能够得到很是好的模型性能。

如今问题来了，我不想用决策树，由于决策树太“硬”了，损失掉了不少输入数据中的几率分布信息，深度DNN的这种复杂非线性组合可以得到更“软”的几率分布拟合能力。

那有什么办法能将更好地将这个先验知识融合到模型中呢？（即强制模型更加关注那个决定性较强的特征维度，而相对忽略其余特征维度）

答案是attention model思想。

inputs = Input(shape=(input_dim,))

# ATTENTION PART STARTS HERE
attention_probs = Dense(input_dim, activation='softmax', name='attention_vec')(inputs)
attention_mul = Multiply()([inputs, attention_probs])
# ATTENTION PART FINISHES HERE

attention_mul = Dense(64)(attention_mul)
output = Dense(1, activation='sigmoid')(attention_mul)
model = Model(input=[inputs], output=output)

咱们在输入层input以后增长了一个Dense层，并使用softmax激活函数，神经元个数=输入向量的维度。这一层的核心做用就是经过softmax从input中选择对target贡献度最大的一个vector dim维度。

以后经过merge该attention model layer和input输入层，经过一个DNN隐层进行综合决策。

经过BP反馈训练后，attention medel layer的权重

import numpy as np

from attention_utils import get_activations, get_data

np.random.seed(1337)  # for reproducibility
from keras.models import *
from keras.layers import Input, Dense, Multiply

input_dim = 32


def build_model():
    inputs = Input(shape=(input_dim,))

    # ATTENTION PART STARTS HERE
    attention_probs = Dense(input_dim, activation='softmax', name='attention_vec')(inputs)
    attention_mul = Multiply()([inputs, attention_probs])
    # ATTENTION PART FINISHES HERE

    attention_mul = Dense(64)(attention_mul)
    output = Dense(1, activation='sigmoid')(attention_mul)
    model = Model(input=[inputs], output=output)
    return model


def main():
    N = 10000
    inputs_1, outputs = get_data(N, input_dim)

    m = build_model()
    m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    print(m.summary())

    m.fit([inputs_1], outputs, epochs=20, batch_size=64, validation_split=0.5)

    testing_inputs_1, testing_outputs = get_data(1, input_dim)
    print "testing_inputs_1", testing_inputs_1
    print "testing_outputs", testing_outputs

    # Attention vector corresponds to the second matrix.
    # The first one is the Inputs output.
    attention_vector = get_activations(m, testing_inputs_1,
                                       print_shape_only=True,
                                       layer_name='attention_vec')[0].flatten()
    print('attention =', attention_vector)

    # plot part.
    import matplotlib.pyplot as plt
    import pandas as pd

    pd.DataFrame(attention_vector, columns=['attention (%)']).plot(kind='bar',
                                                                   title='Attention Mechanism as '
                                                                         'a function of input'
                                                                         ' dimensions.')
    plt.show()


if __name__ == '__main__':
    main()

能够看到，v[1] 得到了绝对的dominate权重

0x2：LSTM/GRU Layer

这个小节咱们对比下在LSTM前/后插入attention model layer，对各个维度的权重关注效果。

from keras.layers import Multiply
from keras.layers.core import *
from keras.layers.recurrent import LSTM
from keras.models import *

from attention_utils import get_activations, get_data_recurrent

INPUT_DIM = 2
TIME_STEPS = 20
# if True, the attention vector is shared across the input_dimensions where the attention is applied.
SINGLE_ATTENTION_VECTOR = False
APPLY_ATTENTION_BEFORE_LSTM = False


def attention_3d_block(inputs):
    # inputs.shape = (batch_size, time_steps, input_dim)
    input_dim = int(inputs.shape[2])
    a = Permute((2, 1))(inputs)
    a = Reshape((input_dim, TIME_STEPS))(a) # this line is not useful. It's just to know which dimension is what.
    a = Dense(TIME_STEPS, activation='softmax')(a)
    if SINGLE_ATTENTION_VECTOR:
        a = Lambda(lambda x: K.mean(x, axis=1), name='dim_reduction')(a)
        a = RepeatVector(input_dim)(a)
    a_probs = Permute((2, 1), name='attention_vec')(a)
    output_attention_mul = Multiply()([inputs, a_probs])
    return output_attention_mul


def model_attention_applied_after_lstm():
    inputs = Input(shape=(TIME_STEPS, INPUT_DIM,))
    lstm_units = 32
    lstm_out = LSTM(lstm_units, return_sequences=True)(inputs)
    attention_mul = attention_3d_block(lstm_out)
    attention_mul = Flatten()(attention_mul)
    output = Dense(1, activation='sigmoid')(attention_mul)
    model = Model(input=[inputs], output=output)
    return model


def model_attention_applied_before_lstm():
    inputs = Input(shape=(TIME_STEPS, INPUT_DIM,))
    attention_mul = attention_3d_block(inputs)
    lstm_units = 32
    attention_mul = LSTM(lstm_units, return_sequences=False)(attention_mul)
    output = Dense(1, activation='sigmoid')(attention_mul)
    model = Model(input=[inputs], output=output)
    return model


if __name__ == '__main__':

    N = 300000
    # N = 300 -> too few = no training
    inputs_1, outputs = get_data_recurrent(N, TIME_STEPS, INPUT_DIM)

    if APPLY_ATTENTION_BEFORE_LSTM:
        m = model_attention_applied_before_lstm()
    else:
        m = model_attention_applied_after_lstm()

    m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    print(m.summary())

    m.fit([inputs_1], outputs, epochs=1, batch_size=64, validation_split=0.1)

    attention_vectors = []
    for i in range(300):
        testing_inputs_1, testing_outputs = get_data_recurrent(1, TIME_STEPS, INPUT_DIM)
        attention_vector = np.mean(get_activations(m,
                                                   testing_inputs_1,
                                                   print_shape_only=True,
                                                   layer_name='attention_vec')[0], axis=2).squeeze()
        print('attention =', attention_vector)
        assert (np.sum(attention_vector) - 1.0) < 1e-5
        attention_vectors.append(attention_vector)

    attention_vector_final = np.mean(np.array(attention_vectors), axis=0)
    # plot part.
    import matplotlib.pyplot as plt
    import pandas as pd

    pd.DataFrame(attention_vector_final, columns=['attention (%)']).plot(kind='bar',
                                                                         title='Attention Mechanism as '
                                                                               'a function of input'
                                                                               ' dimensions.')
    plt.show()

1. Directly on the inputs (same as the Dense example above): `APPLY_ATTENTION_BEFORE_LSTM = True`

直接做用于input层的attention可让咱们得到对输入特征空间的重要性理解。

2. After the LSTM layer: `APPLY_ATTENTION_BEFORE_LSTM = False`

后置的attention layer可让模型的最终决策更加聚焦，将主要的决策权重分配在真正对最终分类有正向帮助的特征维度上，只是这时候，输入attention layer的特征维度是已经通过LSTM抽象过的特征空间，可解释性已经相对较差了。