• TEA Techniques
Navigation
  • Home
  • Browse Techniques
  • Compare Techniques
    • All Categories
    • General
    • Explainability
    • Fairness
    • Privacy
    • Reliability
    • Safety
    • Security
    • Transparency
  • GitHub
Home/Categories/Explainability/Attribution Methods
Explainability

Attribution Methods

Techniques that assign importance scores to inputs/features

3 subcategories • 21 techniques

Gradient Based

Uses gradients/derivatives to compute feature importance (e.g., Integrated Gradients, Saliency Maps)

Model Specific

Leverages specific model architecture for attribution (e.g., Mean Decrease Impurity for trees)

Perturbation Based

Modifies inputs to measure impact on outputs (e.g., SHAP, Permutation Importance)

← Back to Explainability|All categories