Adds an example for Hierarchical Sampling #7244
Merged
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
It compares two epochs of training, with and without Hierarchical Sampling.
for more information, see https://pre-commit.ci
rusty1s
changed the title
|
@rusty1s do you have comments on this simple example? Thank you! |
17 tasks
rusty1s
changed the title
rusty1s
changed the title
rusty1s
approved these changes
May 10, 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Outdated suggestions cannot be applied.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.
It compares one epoch of training with and without Hierarchical Sampling.
With pyg-lib>0.1.0 we return the sampled number of nodes/edges in neighbor_sampler.py
Leveraging this, the training_benchmark.py refers to
BasicGNNbase class, in which the forward pass does the trimming if required (using the--trimflag withtraining_benchmark.py).Therefore, this is an example that mimics what is being done in the
training_benchmark.py,to make evident for the user what this trimming/Hierarchical Sampling is about, how to test it, and have an idea of the advantage.