Is the relatinoal bias still calculated in w/o graph circumstances?
AaronNing opened this issue · 2 comments
AaronNing commented
Hi Qitian,
Thanks for this fantastic work!
In nodeformer.py
line 284:
# compute update by relational bias of input adjacency, requires O(E)
for i in range(self.rb_order):
z_next += add_conv_relational_bias(value, adjs[i], self.b[i], self.rb_trans)
I am a little bit confused that, in w/o graph circumstances (e.g. #2 ,) is the relatinoal bias still calculated?
Thanks.
qitianwu commented
Hi Weixi,
In the w/o graph circumstances you mentioned, the relational bias is not used since we set rb_order=0 (see the run.sh for detailed hyper-parameter settings)
AaronNing commented
I see. Thanks for your quick reply : )