Closed ShunShunJun closed 1 year ago
Hi, sorry for the confusion. Here the individual mean individual heads (which means we have different heads for different channels, see this paper for explanations: https://github.com/cure-lab/LTSF-Linear). We actually use a shared head, but we treat the data in the channel-independent way.
Dear author, I find that in your code you set the hyperparameter individual as 0 defeaultly,but in the paper it is stated that the channel independence has a boost on the effect. Meanwhile, I try to set the individual to 1, but I find that the effect became worse instead,What is the cause of this?