Why is the input to the model with_missing_mask？

[tangkai-RS]

Hi, great job！ I'm a beginner in the field of time-series imputation. May I ask why the "missing_mask" and "X" concat should be used in the input of SAITS?
def impute(self, inputs): X, masks = inputs["X"], inputs["missing_mask"] input_X = torch.cat([X, masks], dim=2) if self.input_with_mask else X input_X = self.embedding(input_X)

[WenjieDu]

Hi there,

Thank you so much for your attention to SAITS! If you find SAITS is helpful to your work, please star⭐️ this repository. Your star is your recognition, which can let others notice SAITS. It matters and is definitely a kind of contribution.

I have received your message and will respond ASAP. Thank you again for your patience! 😃

Best,
Wenjie

[github-actions]

This issue had no activity for 14 days. It will be closed in 1 week unless there is some new activity. Is this issue already resolved?

[WenjieDu]

NaNs are filled with 0. Concatenating missing_mask can tell the model which values are missing.