Closed formath closed 5 years ago
spark word2vec do not support negative sampling, only implemented hierarchical softmax. https://spark.apache.org/docs/2.3.2/mllib-feature-extraction.html#word2vec
Thanks. After random walk, we can use skip gram to generate pair <src_node, positive_node>. How to sample negative nodes for each pair in data processing phase while not in the training phase.
<src_node, positive_node>
negative nodes
spark word2vec do not support negative sampling, only implemented hierarchical softmax. https://spark.apache.org/docs/2.3.2/mllib-feature-extraction.html#word2vec