Question about the output of concatenate

[CYL586309]

From the section 4.1.3 of LINE paper, the first-order proximity and second-order proximity can be preserved by concatenating two embedding vectors of each node. I use concatenate.cpp and obtain a UNIX executable file which produces the final embedding. However, I notice that the embedding vector of each nodes is different from simply combining the first-order and second-order embedding vectors, so I'm curious about the way of concatenating the first-order and second-order embedding vectors. can the authors answer that?

[mnqu]

Thanks for your attention to our work. In practice, the l2 norms of vectors learned with the first- and second-order proximities can be very different, so directly concatenating them may yield inferior results. Therefore, we first normalize both vectors to unit vectors, before concatenating them for classification.

[CYL586309]

Thanks for your answer, I totally understand the values of final embedding.