< Back to Article

Learning supervised embeddings for large scale sequence comparisons

Fig 5

SuperVec(X) 1/2/3 are the SuperVec(X) model trained for node 1, 2 and 3 respectively.

q_i and s_i are the embedding of a query (q) and subject (s) and d_i is the distance of query-subject pair computed at i^th node, d is the similarity score for q and s.

doi: https://doi.org/10.1371/journal.pone.0216636.g005