Kaimaoge
commented
2 years ago Yes, we must know the spatial location of the test nodes. Otherwise, there will be no information for Kriging. The statement you are referring to means that we did not know the exact spatial location during training. However, unknown locations should be given when we apply our model. The 207 nodes contain unseen nodes during training.
On Sat, Nov 27, 2021 at 10:35 PM HuangLongji @.***> wrote:
In section 3.2, "As we can not exactly know the spatial locations of test nodes, Wsample is also randomly generated to make the learning samples generalizable to more cases." was given. However, I found the adjacent matrix is all node's spatial location in testing. For example, the dims for adj matrix of METR is 207*207. The spatial locations of test nodes are given?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/Kaimaoge/IGNNK/issues/4, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACSYV3LXWGAQDNNTAJ5H6SLUOGPOLANCNFSM5I4Z76CA .
-- Kind regards
Wu Yuankai
In section 3.2, "As we can not exactly know the spatial locations of test nodes, Wsample is also randomly generated to make the learning samples generalizable to more cases." was given. However, I found the adjacent matrix is all node's spatial location in testing. For example, the dims for adj matrix of METR is 207*207. The spatial locations of test nodes are given?