Skip to content

ENH: Refactor Adversarial Debiasing(#4) - #15

Open
Chirag-agg wants to merge 1 commit into
usarfoss:mainfrom
Chirag-agg:issue-4-fix
Open

ENH: Refactor Adversarial Debiasing(#4)#15
Chirag-agg wants to merge 1 commit into
usarfoss:mainfrom
Chirag-agg:issue-4-fix

Conversation

@Chirag-agg

@Chirag-agg Chirag-agg commented Oct 15, 2025 •
edited
Loading

Copy link
Copy Markdown

Description

  • Issue: ENH refactor Adversarial Debiasing #4
  • Predictor and adversary networks are created after preprocessing, so input_dim and sensitive_dim are correctly set.
  • Supports arbitrary loss functions via loss_fn and fairness_loss_fn parameters.
  • Models and tensors are device-aware, using GPU if available.
  • Added new tests in test_adversarial_fairness.py to validate basic fit/predict functionality, categorical preprocessing, and sensitive features.

Tests

  • new tests added
  • existing tests adjusted

Documentation

  • no documentation changes needed

Screenshots

  • Not applicable

@Chirag-agg Chirag-agg changed the title ENH: Refactor Adversarial Debiasing #4 ENH: Refactor Adversarial Debiasing Oct 15, 2025
@Chirag-agg Chirag-agg changed the title ENH: Refactor Adversarial Debiasing ENH: Refactor Adversarial Debiasing #15 Oct 15, 2025
@Chirag-agg Chirag-agg changed the title ENH: Refactor Adversarial Debiasing #15 ENH: Refactor Adversarial Debiasing Oct 15, 2025
@Chirag-agg Chirag-agg changed the title ENH: Refactor Adversarial Debiasing ENH: Refactor Adversarial Debiasing(#4) Oct 15, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@Chirag-agg