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

DeepGraphInfomax GNNModular pretraining task #3358

Merged
merged 15 commits into from
Apr 24, 2023

Conversation

tonydavis629
Copy link
Collaborator

Description

Adds in the unsupervised deepgraphinfomax pretraining task for GNNModular. This maximizes the mutual information between positive (same graph) and negative (different graphs) graph representations.

Type of change

Please check the option that is related to your PR.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
    • In this case, we recommend to discuss your modification on GitHub issues before creating the PR
  • Documentations (modification for documents)

Checklist

  • My code follows the style guidelines of this project
    • Run yapf -i <modified file> and check no errors (yapf version must be 0.32.0)
    • Run mypy -p deepchem and check no errors
    • Run flake8 <modified file> --count and check no errors
    • Run python -m doctest <modified file> and check no errors
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • I have added tests that prove my fix is effective or that my feature works
  • New unit tests pass locally with my changes
  • I have checked my code and corrected any misspellings

Copy link
Member

@rbharath rbharath left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Some comments mostly around modification to the docs and requests for more unit tests

deepchem/models/torch_models/gnn.py Show resolved Hide resolved
deepchem/models/torch_models/gnn.py Show resolved Hide resolved
"""
The forward method takes two inputs, `x` (local node representations) and `summary` (global graph representations), both of shape `(batch_size, hidden_dim)`.
It computes the product of `summary` and `self.weight`, and then calculates the element-wise product of `x` and the resulting matrix `h`.
Finally, it returns the sum of the element-wise product along dimension 1 (i.e., summing over the `hidden_dim`), resulting in a tensor of shape `(batch_size,)`, which represents the similarity scores between the local and global representations.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add a numpydoc style Parameters field here?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

deepchem/models/torch_models/gnn.py Show resolved Hide resolved
deepchem/models/torch_models/gnn.py Show resolved Hide resolved
deepchem/models/losses.py Show resolved Hide resolved
@@ -178,6 +180,36 @@ def forward(self, data):
return out


class Discriminator(nn.Module):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you add a unit test for this layer?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

deepchem/models/torch_models/gnn.py Show resolved Hide resolved
Copy link
Member

@rbharath rbharath left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Feel free to merge in once CI looks clear

@tonydavis629 tonydavis629 merged commit 30835b3 into deepchem:master Apr 24, 2023
@tonydavis629 tonydavis629 deleted the deepinfo branch April 24, 2023 22:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants