The label issue of Wikipedia dataset

[baojianzhou]

Dear Authors,

I have a question about the performance of the Wikipedia dataset shown in Table 3 of your paper. I ran your code and successfully reproduced results. However, when I tried to apply the learned embedding to Deepwalk scoring.py, I got pretty low Micro-F1 scores. I dug it out that there are two potential reasons: 1) You may have some error in your wikipedia.cmty. To check it, the label id 39 should contain node 77, not 2933; 2) Maybe there is something wrong with my code. Could you help to confirm 1)? Thank you!