[阿里DIEN] 深度兴趣进化网络源码分析 之 Keras版本

class AttentionSequencePoolingLayer(Layer):
    """The Attentional sequence pooling operation used in DIN.

      Input shape
        - A list of three tensor: [query,keys,keys_length]
        - query is a 3D tensor with shape:  ``(batch_size, 1, embedding_size)``
        - keys is a 3D tensor with shape:   ``(batch_size, T, embedding_size)``
        - keys_length is a 2D tensor with shape: ``(batch_size, 1)``

      Output shape
        - 3D tensor with shape: ``(batch_size, 1, embedding_size)``.

      Arguments
        - **att_hidden_units**:list of positive integer, the attention net layer number and units in each layer.
        - **att_activation**: Activation function to use in attention net.
        - **weight_normalization**: bool.Whether normalize the attention score of local activation unit.
        - **supports_masking**:If True,the input need to support masking.

      References
        - [Zhou G, Zhu X, Song C, et al. Deep interest network for click-through rate prediction[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2018: 1059-1068.](https://arxiv.org/pdf/1706.06978.pdf)
    """

    def __init__(self, att_hidden_units=(80, 40), att_activation='sigmoid', weight_normalization=False,
                 return_score=False,
                 supports_masking=False, **kwargs):
        self.att_hidden_units = att_hidden_units
        self.att_activation = att_activation
        self.weight_normalization = weight_normalization
        self.return_score = return_score
        super(AttentionSequencePoolingLayer, self).__init__(**kwargs)
        self.supports_masking = supports_masking

    def build(self, input_shape):
        if not self.supports_masking:
            if not isinstance(input_shape, list) or len(input_shape) != 3:
                raise ValueError('...)
            if len(input_shape[0]) != 3 or len(input_shape[1]) != 3 or len(input_shape[2]) != 2:
                raise ValueError(...)
            if input_shape[0][-1] != input_shape[1][-1] or input_shape[0][1] != 1 or input_shape[2][1] != 1:
                raise ValueError(...)
        else:
            pass
        self.local_att = LocalActivationUnit(
            self.att_hidden_units, self.att_activation, l2_reg=0, dropout_rate=0, use_bn=False, seed=1024, )
        super(AttentionSequencePoolingLayer, self).build(
            input_shape)  # Be sure to call this somewhere!

    def call(self, inputs, mask=None, training=None, **kwargs):
        if self.supports_masking:
            if mask is None:
                raise ValueError(...)
            queries, keys = inputs
            key_masks = tf.expand_dims(mask[-1], axis=1)

        else:
            queries, keys, keys_length = inputs
            hist_len = keys.get_shape()[1]
            key_masks = tf.sequence_mask(keys_length, hist_len)

        attention_score = self.local_att([queries, keys], training=training)
        outputs = tf.transpose(attention_score, (0, 2, 1))

        if self.weight_normalization:
            paddings = tf.ones_like(outputs) * (-2 ** 32 + 1)
        else:
            paddings = tf.zeros_like(outputs)
        outputs = tf.where(key_masks, outputs, paddings)

        if self.weight_normalization:
            outputs = tf.nn.softmax(outputs)
        if not self.return_score:
            outputs = tf.matmul(outputs, keys)
        outputs._uses_learning_phase = attention_score._uses_learning_phase

        return outputs