The GCN submission for ogbn-arxiv reports 142,888 parameters on the leader-board. Looking at the code and default settings, it seems to use the following architecture:
This architecture gives a total number of parms of 110,120, which is 32,768 fewer than that reported on the leader-board. It's probably not a coincidence that this number is equal to the input*hidden dimensions. Is there some other projection layer coming into play, is the leader-board mistaken, or something else?
The GCN submission for ogbn-arxiv reports 142,888 parameters on the leader-board. Looking at the code and default settings, it seems to use the following architecture:
This architecture gives a total number of parms of 110,120, which is 32,768 fewer than that reported on the leader-board. It's probably not a coincidence that this number is equal to the input*hidden dimensions. Is there some other projection layer coming into play, is the leader-board mistaken, or something else?