Adaptive Embedding Aggregation Fusion module

[wendongj]

Hi, dear, author, really thanks for sharing the result of this paper, it is an exciting work. I click this github page many times everyday to see if the code is updated.... I am confusing about Adaptive Embedding Aggregation Fusion module, in formula 13, as my understanding, Q is fixed embedding, it is one dimensional, K is reshaped into two dimensional, then how can them multiply together?

[HaoFengyuan]

As described in our paper, the dimensions of K and V are (D, T×F), while Q can be interpreted as (1, D), resulting in a final output shape of (1, D). We utilized nn.MultiheadAttention for this operation. Code updates will be made available once our paper is received.

[wendongj]

As described in our paper, the dimensions of K and V are (D, T×F), while Q can be interpreted as (1, D), resulting in a final output shape of (1, D). We utilized nn.MultiheadAttention for this operation. Code updates will be made available once our paper is received.

I see, thanks for your reply^_^