Mitigating bias
We can mitigate bias at three different levels with methods that operate at these individual levels:
- Preprocessing: These are interventions to detect and remove bias from the training data before training the model. Methods that leverage preprocessing have the advantage that they tackle bias at the source. On the other hand, any undetected bias is still amplified by the model.
- In-processing: These methods mitigate bias during the model training and are, therefore, highly dependent on the model and tend to not be model-agnostic like the preprocessing and post-processing methods. They also require hyperparameter tuning to calibrate fairness metrics.
- Post-processing: These methods mitigate bias during model inference. In Chapter 7, Anchors and Counterfactual Explanations, we touched on the subject of using the What-If tool to choose the right thresholds (see Figure 7.14 in that chapter), and we manually adjusted them to achieve parity with false positives...
