1 dépôt
Awesome GitHub RepositoriesDeepLiftSHAP Attribution Methods
Extends DeepLift to approximate SHAP values by averaging attributions across multiple baseline-input pairs.
Distinct from Computed Attribute Derivation: Distinct from Computed Attribute Derivation: focuses on a specific SHAP approximation method for neural networks, not general attribute derivation.
Explore 1 awesome GitHub repository matching software engineering & architecture · DeepLiftSHAP Attribution Methods. Refine with filters or upvote what's useful.
Awesome DeepLiftSHAP Attribution Methods GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- pytorch/captum
pytorch/captum
5,652Voir sur GitHubCaptum is an open-source library for explaining model predictions by attributing them to input features, neurons, and layers using gradient-based and perturbation-based methods. It provides a modular framework for implementing, evaluating, and combining a range of explanation techniques, including gradient-based attribution, perturbation-based analysis, game-theoretic Shapley value approximation, and surrogate model explanations, with support for parallelization and noise stabilization. The library distinguishes itself through its breadth of attribution methods and its support for advanced in
Approximates SHAP values by averaging DeepLift attributions across multiple baseline-input pairs.
Python
