Why are the accuracies so low in your paper?

[Sleepychord]

1.I found the accuracies of node classification are only about 20% for all algorithms. But how to define "accuracy" of a muti-label dataset? 2.I remembered that if training:test = 9:1 then the F1-macro of deep walk should be around 0.28 in its paper... Did I misunderstand something?

[songzenghui]

Note the embedding size in this paper