About graph_pair_sim function

[zzh-ecnu]

Hello~An excellent work!

When reading your code, i find that the implement of function "graph_pair_sim" is different from loss.py and match_fn.py

Code in match_fn.py

dis_loc = (loc_dis_mat * weight_mat).mean()

Code in loss.py

dis_loc = (loc_dis_mat * weight_mat).sum()

I think cause goal of script is different, so when matching it is mean(), and when calculating loss it is sum(), all right？

[RenMin1991]

Yes.

We find that the distances between structures of feature graphs are more important during training than matching.
Hence, mean() decreases the weight of distances between structures of feature graphs comparing to sum().