pulsatrix 1.1.0
Loading...
Searching...
No Matches
Model-Agnostic Explainers

Tools that don't depend on a particular explainer: perturbation explainers that only need a model's input/output behavior, explanation-quality metrics (faithfulness, randomization, complexity), the null-model baseline, and dense matrix decompositions for analysing activations and weights. More...

Collaboration diagram for Model-Agnostic Explainers:

Files

file  anchors.hpp
 Anchors (Ribeiro, Singh and Guestrin, "Anchors: High-Precision Model-Agnostic Explanations", AAAI 2018): an if-then rule around one input that keeps the model's prediction with high probability, whatever the other features do (XAI-4).
 
file  explanation_agreement.hpp
 Whether two models explain the same inputs with the same evidence (roadmap KD-2): a distilled student against its teacher, a fine-tuned model against its base, or any two models that take the same input.
 
file  explanation_metrics.hpp
 Explanation-quality metrics in the Quantus families (roadmap XAI-5): faithfulness (deletion and insertion curves, with ROAD's imputation), randomization (the model-parameter randomization test) and complexity (sparseness and complexity).
 
file  global_sensitivity.hpp
 Global sensitivity analysis: Morris elementary effects and Sobol indices (CFS-4).
 
file  ice.hpp
 Individual conditional expectation (ICE), its centered and derivative forms, two-feature partial dependence (CFS-1) and accumulated local effects (CFS-2).
 
file  kernel_shap.hpp
 KernelSHAP – model-agnostic Shapley value approximation via weighted linear regression (charter Part 1, Phase 3; theory: xai_context.aDNA's technique_shap.md).
 
file  lime.hpp
 LIME – local interpretable model-agnostic explanations (charter Part 1, Phase 3; theory: xai_context.aDNA's technique_lime.md).
 
file  linear_algebra.hpp
 Small, dense linear-system solve – shared by weighted_linear_regression.hpp (Phase 3's LIME/KernelSHAP) and gaussian_process.hpp (this campaign's GP-BO surrogate).
 
file  matrix_decompositions.hpp
 Small dense decompositions on the host: symmetric eigensolver, power iteration, QR and SVD (roadmap FND-4).
 
file  null_model_baseline.hpp
 The baseline rule as one call (roadmap XAI-6): run any explainer, probe or featurizer on the trained model and on a re-initialized ("null") model, and compare.
 
file  pdp.hpp
 Partial Dependence Plot – a global marginal-effect technique, sweeping one feature's value while averaging the model's response over a background set (charter addition 2026-09-19, see charter Decisions Log).
 
file  prototypes.hpp
 Explaining by example (XAI-4): the background inputs nearest one input that the model treats the same way and differently, and ProtoDash's weighted prototypes that summarize a dataset (Gurumoorthy, Dhurandhar, Cecchi and Aggarwal, ICDM 2019).
 
file  rule_extraction.hpp
 Rules from trees, run by the Datalog engine (roadmap KD-3): a surrogate or distilled tree becomes a Datalog program that classifies the same way.
 
file  sensitivity.hpp
 Local sensitivity: one-at-a-time input changes and occlusion (CFS-3).
 
file  surrogate_tree.hpp
 A global surrogate: a shallow decision tree fitted to a model's predictions, with its fidelity to the model on held-out inputs (XAI-4; TREPAN, Craven and Shavlik 1996).
 
file  weighted_linear_regression.hpp
 Weighted least squares via normal equations – the shared fitting primitive Phase 3's LIME and KernelSHAP explainers both reduce to.
 

Detailed Description

Tools that don't depend on a particular explainer: perturbation explainers that only need a model's input/output behavior, explanation-quality metrics (faithfulness, randomization, complexity), the null-model baseline, and dense matrix decompositions for analysing activations and weights.