Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

updating dataset to just be pyg Dataset object #34

Merged
merged 14 commits into from
May 15, 2023
Merged

updating dataset to just be pyg Dataset object #34

merged 14 commits into from
May 15, 2023

Conversation

shenyangHuang
Copy link
Owner

to run with pyg data
instead of data = dataset.data[0], we now have data = dataset.get_TemporalData()
reworked the pyg dataaset to not use inMemoryDataset

…he edge labels, all one tensor) are called edge_label
…yG and numpy format, reworked the documentation
@shenyangHuang
Copy link
Owner Author

shenyangHuang commented May 14, 2023

removing unnecessary arguments in NegativeEdgeSampler_RND including device

@shenyangHuang
Copy link
Owner Author

major changes: NegativeSampler are now initialized in the dataset.py
The usage pattern is as follows:

dataset = PyGLinkPropPredDataset(name=name, root="datasets")
neg_sampler = dataset.negative_sampler
dataset.load_val_ns()
dataset.load_test_ns() 
neg_sampler.query_batch(pos_batch, split_mode=split_mode)

@fpour fpour merged commit 2c02d63 into main May 15, 2023
shenyangHuang pushed a commit that referenced this pull request Jun 26, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ASAP As soon as possible
Projects
None yet
2 participants