Closed BenchengY closed 7 years ago
We follow the experimental procedure in http://www.public.asu.edu/~huanliu/papers/kdd09.pdf. According to their paper:
To avoid the affection of thresholding, we assume the number of labels on the test data are already known and check how the top-ranking predictions match with the true labels.
ok, thanks!
I notice that some nodes in the blogcatalog may have more than one label (group), in that case, i just want to know how you process this nodes in classification as the have many labels? thanks!