NLNR

Hi, is there any progress about the efficient version?

Actually it will not make all the nodes into a single line and put them into GRU. Instead, only locally adjacent nodes are put into GRU at one time.

It is set to 0.5 to equally weight the two part. There may be better combination.

The sessions for yoochoose are exactly the same in the paper of sr-gnn. The preprocess code is provided.

same question