Closed ninamiolane closed 1 year ago
Hi, I'm one of the implementers of SCCN.
I believe that SCN and SCCN are two different models from Yang et al 2022. There is some confusion in that they are both labelled SCN in Figure 11 of the Architectures of Topological Deep Learning paper. SCCN should be the leftmost "SCN" in that figure.
Thank you very much for stepping in! This is incredibly helpful. I see the two models in Yang et al. 2022 and the confusion arising from their misnaming in Figure 11. Thus:
Thus, TODOs for us:
We will update the Figure 11 offline.
What?
There were two implementations of SCN by challenge participants:
However, we should check that the difference between these two implementations only lies in the ranks used.
Why?
Because it is confusing to have two very close implementations of SCN without knowing their precise difference.
Where?
The files to modify are:
How?
We should look at the following: