Difference between GCN_APPRO and GCN_APPRO_MIX

[zhongyingji]

It seems that the paper used GCN_APPRO(two sample layer), while the code uses GCN_APPRO_MIX, what is the difference between two methods, does the ultimate result varies a lot?

[matenure]

GCN_APPRO: approximate two layers GCN_APPRO_MIX: precomputation in the bottom layer GCN_APPRO_MIX is generally faster and more accurate.