After indexing change negative generation for NeuroMF got a bug.
Before: negatives were sampled from [0, num_items) uniform distribution; for now it is from [0, max_item + 1) distribution.
Ids were consecutive before and now they are not, so we can sample absent ids, which can break a training or make it less efficient.
Here:
After indexing change negative generation for NeuroMF got a bug. Before: negatives were sampled from [0, num_items) uniform distribution; for now it is from [0, max_item + 1) distribution. Ids were consecutive before and now they are not, so we can sample absent ids, which can break a training or make it less efficient. Here: