Add sampled input to DistNeighborSampler._sample_from_nodes #160
Conversation
This file contains hidden or 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
|
|
kmontemayor2-sc
commented
May 5, 2025
| if edge_dir == 'out': | ||
| data[res_edge_type]['edge_label_index'] = \ | ||
| torch.stack((v[1], v[0]), dim=0) | ||
| if isinstance(input_type, tuple): |
There was a problem hiding this comment.
Making this change as input_type can also be a NodeType or None, both of which will throw if passed into reverse_edge_type.
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Outdated suggestions cannot be applied.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.
I want to do this as I'd like to be able to maintain a full copy of the inputs to the sampling function - and AFAICT we do not currently store this anywhere.
My usecase here is that I have some specially constructed tensor which contains labels to sample against, and I'd like to be able to identify the "label nodes".
The tensor looks something like:
[<src_node>, <padding>, <positive_labels>, ...], and since this.nodeand.batchget deduped somewhere (idk where) I cannot reconstruct the labels per src node otherwise.