Compensated Integrated Gradients to Reliably Interpret EEG Classification

Understand

Integrated gradients are widely employed to evaluate the contribution of input features in classification models because it satisfies the axioms for attribution of prediction.

• This method, however, requires an appropriate baseline for reliable determination of the contributions.
• We propose a compensated integrated gradients method that does not require a baseline.
• In fact, the method compensates the attributions calculated by integrated gradients at an arbitrary baseline using Shapley sampling.