Improve explanations

When you are working with AutoML image models, you can configure specific parameters to improve your explanations.

The Vertex Explainable AI feature attribution methods are all based on variants of Shapley values. Because Shapley values are very computationally expensive, Vertex Explainable AI provides approximations instead of the exact values.

You can reduce the approximation error and get closer to the exact values by changing the following inputs:

  • Increasing the number of integral steps or number of paths.

Increasing steps

To reduce approximation error, you can increase:

  • the Number of integral steps in the UI

What's next