# Why softmax in YouTube’s DNN recommender

I am confused about the softmax layer of YouTube’s DNN candidate generation. A user may interact with many videos. Softmax is assuming classes are exclusive. For example, logits = [[4.0, 4.0, 1.0]], labels = [[1.0, 1.0, 0.0]], the sigmoid cross entropy loss is 0.45 while softmax cross entropy loss is 1.43.

Is it because in the candidate generation stage, the relative order of items does not matter?