Add configurable fixed and k-fold splits for omics datasets - #134
Merged
Conversation
Keep the historical 70/15/15 cache path as the default while letting each run pick a 3/1/1 test fold, and share that split between graphs and sklearn baselines. Co-authored-by: Cursor <cursoragent@cursor.com>
johmathe
approved these changes
Sep 11, 2026
| num_nodes: | ||
| ${calculate_num_nodes:${dataset.parameters.num_samples},${dataset.loader.parameters.train_val_test_split},${dataset.loader.parameters.node_sample_ratio}, | ||
| ${dataset.parameters.full_num_nodes}} | ||
| num_nodes: ${calculate_num_nodes:${dataset.parameters.num_samples},${dataset.loader.parameters.train_val_test_split},${dataset.loader.parameters.node_sample_ratio},${dataset.parameters.full_num_nodes},${dataset.split_params.split_type},${dataset.split_params.k}} |
Collaborator
There was a problem hiding this comment.
note for later, these are not the most readable...
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
compute_omics_split_indices: defaultfixedis still shuffle-42 then 70/15/15 (same cache path);k-foldis a stratified 3/1/1 rotation wheredata_seedis the test fold.sync_num_nodes_from_datasetkeep LayerNorm/flatten dims aligned when train size is not exactly 70%.groupingplumbing is present but defaults tonullon every omics dataset. Hub revision is unchanged.Test plan
pytest tests/data/test_omics_split_indices.py tests/utils/test_num_nodes_sync.py tests/data/test_dataset_config_consistency.pypython -m ogbench dataset=brca model=gcnpython -m ogbench dataset=brca model=gcn dataset.split_params.split_type=k-fold dataset.split_params.data_seed=0