View Categories

AI – Stability Property

Stability” (another important element in TRUST) compares explanations between similar instances for a fixed model (while “Consistency“, see AI_9, compares explanations between models). High stability means that slight variations in the features of an instance do not substantially change the explanation (unless these slight variations also strongly change the prediction).

See (Du et al. 2022) and (Gyllenhammar et al., 2020).

Main Question

Is a high stability achieved?

Sub-Questions:

  1. Are the explanations similar for similar instances?
  2. Is the explanation strongly affected by slight changes of the feature values of the instance to be explained?
  3. Is the explanation strongly affected by the non-deterministic components of the explanation method?

References