SakurajimaMaiii

In https://github.com/wyf0912/LDDG/blob/0242b2b739953a3545c954b5487f58600e981692/train_lddg.py#L164 why only use fisrt 2000 features, not all ? just to reduce compuation ?

Hi, authors, thanks for sharing code. I found a minor typo in paper (https://arxiv.org/pdf/2203.13591.pdf). In the caption of Tabel 2, "Tesults are evaluated", Tesults should be Results?

Question about number of meta train and meta test

1

Thanks for your great work and code release. I have a question about training process. In [this ](https://github.com/liuquande/SAML/blob/263764b9fcdb566864a31eedb347ac4674ca77ea/train.py#L41) why num_meta_train is 2 ? **Totally we have 5 source domains during...