explainiverse 0.7.1__py3-none-any.whl → 0.8.1__py3-none-any.whl

explainiverse/__init__.py

@@ -2,9 +2,10 @@
 """
 Explainiverse - A unified, extensible explainability framework.
 
-Supports multiple XAI methods including LIME, SHAP, TreeSHAP, Anchors, 
-Counterfactuals, Permutation Importance, PDP, ALE, and SAGE through a 
-consistent interface.
+Supports 18 state-of-the-art XAI methods including LIME, SHAP, TreeSHAP,
+Integrated Gradients, DeepLIFT, DeepSHAP, LRP, GradCAM, TCAV, Anchors,
+Counterfactuals, Permutation Importance, PDP, ALE, SAGE, and ProtoDash
+through a consistent interface.
 
 Quick Start:
     from explainiverse import default_registry
@@ -33,7 +34,7 @@ from explainiverse.adapters.sklearn_adapter import SklearnAdapter
 from explainiverse.adapters import TORCH_AVAILABLE
 from explainiverse.engine.suite import ExplanationSuite
 
-__version__ = "0.7.1"
+__version__ = "0.8.1"
 
 __all__ = [
     # Core

explainiverse/core/registry.py

@@ -375,6 +375,7 @@ def _create_default_registry() -> ExplainerRegistry:
     from explainiverse.explainers.gradient.smoothgrad import SmoothGradExplainer
     from explainiverse.explainers.gradient.saliency import SaliencyExplainer
     from explainiverse.explainers.gradient.tcav import TCAVExplainer
+    from explainiverse.explainers.gradient.lrp import LRPExplainer
     from explainiverse.explainers.example_based.protodash import ProtoDashExplainer
     
     registry = ExplainerRegistry()
@@ -587,6 +588,23 @@ def _create_default_registry() -> ExplainerRegistry:
         )
     )
     
+    # Register LRP (Layer-wise Relevance Propagation)
+    registry.register(
+        name="lrp",
+        explainer_class=LRPExplainer,
+        meta=ExplainerMeta(
+            scope="local",
+            model_types=["neural"],
+            data_types=["tabular", "image"],
+            task_types=["classification", "regression"],
+            description="LRP - Layer-wise Relevance Propagation for decomposition-based attributions (requires PyTorch)",
+            paper_reference="Bach et al., 2015 - 'On Pixel-wise Explanations for Non-Linear Classifier Decisions by Layer-wise Relevance Propagation' (PLOS ONE)",
+            complexity="O(n_layers * forward_pass)",
+            requires_training_data=False,
+            supports_batching=True
+        )
+    )
+    
     # =========================================================================
     # Global Explainers (model-level)
     # =========================================================================

explainiverse/explainers/gradient/__init__.py

@@ -13,6 +13,7 @@ Explainers:
     - SmoothGradExplainer: Noise-averaged gradients
     - SaliencyExplainer: Basic gradient attribution
     - TCAVExplainer: Concept-based explanations (TCAV)
+    - LRPExplainer: Layer-wise Relevance Propagation
 """
 
 from explainiverse.explainers.gradient.integrated_gradients import IntegratedGradientsExplainer
@@ -21,6 +22,7 @@ from explainiverse.explainers.gradient.deeplift import DeepLIFTExplainer, DeepLI
 from explainiverse.explainers.gradient.smoothgrad import SmoothGradExplainer
 from explainiverse.explainers.gradient.saliency import SaliencyExplainer
 from explainiverse.explainers.gradient.tcav import TCAVExplainer, ConceptActivationVector
+from explainiverse.explainers.gradient.lrp import LRPExplainer
 
 __all__ = [
     "IntegratedGradientsExplainer", 
@@ -31,4 +33,5 @@ __all__ = [
     "SaliencyExplainer",
     "TCAVExplainer",
     "ConceptActivationVector",
+    "LRPExplainer",
 ]