For dcn model about dnn_ctr HOT 5 OPEN

The x_l's size should be batch_size * [field_size * embedding_size]，in DCN paper，x_l's size should be [filed_sizeembedding], so result of x_0x_l^T is rank-one. Thinking of expanding to batch_size [field_sizeembedding_size], the result's size should be batch_size1. If use torch.matmul(x_0, x_l.t()), the size is wrong.

from dnn_ctr.

@jiarenyf

from dnn_ctr.

The shapes of x0, xl, wl, bl are all [fieldSzie*embeddingSize, 1] (ignoring the batch_axis), and the formulation of xl should be xl = matmul(matmul(x0, xl.T), wl) + bl + xl, as shown in the following image:
...

I am not familiar with pytorch, but in mxnet I use batch_dot to implement the calculation of xl, as in here ...

from dnn_ctr.

@jiarenyf The x_0 in my code is two-dimension . And I do the same thing as batch_dot in my code

from dnn_ctr.

But the result of x0*xl^T is not rank-one, it should be [batchSize, fieldSize*embeddingSize, fieldSize*embeddingSize], and the shape of x0*xl^T*wl is [batchSize, fieldSize*embeddingSize] ... Here I use * to represent matmul ...

from dnn_ctr.