Is there any difference on semi-supervised decoders' inputs?

[YuzhengSun]

Dim_reduction adds a representation part before decoder compared to normal semi-supervised model. However, the inputs of decoders are all addition between tensors, is there any difference? I think normal semi-supervised model's decoder's input should be addition of dimensions (dim_z + dim_y), but I'm not sure.

[musyoku]

Do you mean

The input of the normal semi-supervised model should be a concatenation of y and z input = concatenate(z, y) But in dimensionality reduction example, the input of decoders are calculated by adding y and z input = z + y Is there any difference?

?