Use observation mask as feature in DeepAR #2892
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
abdulfatir
force-pushed
the
mask-feat-deepar
branch
from
0e859d3
to
15204d5
Compare
Does the dataset contain missing values? |
lostella
added
BREAKING
|
No, it does not, so this only testing the padding aspect. |
TonyHCIR
approved these changes
May 28, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description of changes:
This PR adds the observation mask as an input feature to DeepAR. Previously lags were fed into the model but the model had no information on whether the lag value is observed or missing/padded.
I ran a small experiment to gauge the performance with and without (previous version) the mask feature. Here are the results on the solar dataset averaged over 10 runs. Each model was trained for 10 epochs.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.
Please tag this pr with at least one of these labels to make our release process faster: BREAKING, new feature, bug fix, other change, dev setup