Chih-Ming Chen
Thanks for the feedback. Could you show me what gcc version you used? I'll have a check later.
The current version doesn't provide the API for computing prediction scores. To compute it, just get the inner product of user and item representations.
In this tool, one update contains 1 positive sample and 1\*N negative samples. Suppose sample_times is set to 10, then it runs 10 million updates. For Hop-Rec, one update contains...
What does the indicator function mean? Could you give me a concrete example?
We will cumulate the log-loss when the corresponding condition holds.
Increasing the -walk_times (maybe > 10 or 20) and -sample_times usually helps. BTW, if you test it on a public dataset, please tell me which dataset you used. I am...
Thanks for the feedbacks, I'll have a check.
do you have the link of the dataset? I can test it later
so now we change the default version to "train stage 1 and then to train stage 2" ? or we'll have an option to do this?
It depends on the task you test. Try using the keywords such as: - word embeddings - link prediction - network reconstruction