kernel_shap.hpp File Reference

KernelSHAP – model-agnostic Shapley value approximation via weighted linear regression (charter Part 1, Phase 3; theory: xai_context.aDNA's technique_shap.md). More...

#include <cstdint>
#include <functional>
#include <stdexcept>
#include <string>
#include <vector>
#include "pulsatrix/assert.hpp"
#include "pulsatrix/attribution.hpp"
#include "pulsatrix/device_backend.hpp"
#include "pulsatrix/tensor.hpp"
#include "pulsatrix/weighted_linear_regression.hpp"

Include dependency graph for kernel_shap.hpp:

Go to the source code of this file.

Classes
class	pulsatrix::KernelSHAP
	Approximates Shapley values via full coalition enumeration + SHAP-kernel-weighted linear regression, reusing fit_weighted_linear_regression for the reduced (n-1)-dimensional problem the efficiency-axiom substitution produces. More...

Namespaces
namespace	pulsatrix
namespace	pulsatrix::detail

Functions
double	pulsatrix::detail::BinomialCoefficient (int64_t n, int64_t k)
	Binomial coefficient C(n,k), computed iteratively to avoid factorial overflow.
float	pulsatrix::detail::ShapKernelWeight (int64_t n, int64_t coalition_size)
	The SHAP kernel pi(z') = (n-1) / [C(n,|z'|) * |z'| * (n-|z'|)], for 1 <= |z'| <= n-1.

Detailed Description

KernelSHAP – model-agnostic Shapley value approximation via weighted linear regression (charter Part 1, Phase 3; theory: xai_context.aDNA's technique_shap.md).