ml-fairness-framework
FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)
- 71
- Jupyter Notebook
- 5 y ago
FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)
End-to-end responsible-AI audit of a DistilBERT toxicity classifier: identity-group bias audit, adversarial attacks, mitigation techniques, and a production guardrail pipeline. Built on the Jigsaw Unintended Bias in Toxicity Classification dataset.