Are word2vec embeddings the same if i re-train on the same sentences?

Question

If I give the same sentences to a word2vec model and train it 2 different times (of course with the same vector size), do I obtain the same embeddings for words?

Answer 1

There are several stochastic processes during word2vec training. First, the embeddings are randomly initialized, second, negative sampling is used to approximate the denominator in the softmax term. Only if those random processes, start with the same seed, the vectors will be exactly the same.

Otherwise, the training will converge to totally different vectors, however, the distances between the vectors will always be approximately the same.