IG_i(x) = (x_i - baseline_i) * (1/steps) * sum_{k=1}^{steps} d(F(baseline + (k/steps)(x - baseline)))/dx_i – a Riemann-sum approximation of the straight-line path integral from baseline to input. More...

#include <integrated_gradients.hpp>

Public Member Functions
Attribution	explain (ExplainerContext &ctx, const Tensor &input, const Tensor &baseline, int64_t target_index, int64_t steps, DeviceBackend *backend) const
	Computes the Integrated Gradients attribution for one output index.

Detailed Description

IG_i(x) = (x_i - baseline_i) * (1/steps) * sum_{k=1}^{steps} d(F(baseline + (k/steps)(x - baseline)))/dx_i – a Riemann-sum approximation of the straight-line path integral from baseline to input.

Note: Reuses Saliency::explain per interpolation step (each step's gradient IS exactly a raw-gradient saliency computation at one interpolated point) rather than reimplementing the forward/backward mechanics.; Correctness is verified via the completeness axiom (sum(IG(x)) == F(x) - F(baseline)), not just "it runs" – see vision_integrated_gradients.md.; A pure graph walker built entirely against ExplainerContext/Saliency's public interfaces – no core (Tensor/ComputationGraph/Autograd/Module) changes needed.; Device-generic host boundary: input/baseline are read to the host once, each interpolated point is uploaded beside the input, gradients accumulate on the device, and the final (x - baseline) * avg_grad product runs on one host read of the sum.

Member Function Documentation

◆ explain()

Attribution pulsatrix::IntegratedGradients::explain	(	ExplainerContext &	ctx,
		const Tensor &	input,
		const Tensor &	baseline,
		int64_t	target_index,
		int64_t	steps,
		DeviceBackend *	backend
	)		const

inline

Computes the Integrated Gradients attribution for one output index.

Parameters

ctx	Context to run each interpolation step's forward/backward pass through.
input	Input to explain.
baseline	Reference "uninformative" input. Must match input's shape.
target_index	Which output element to attribute (0-based, flat index).
steps	Number of Riemann-sum interpolation steps (50-300 typical; more steps tightens the completeness-axiom approximation error).
backend	Backend to allocate intermediate tensors through.

Returns: An Attribution with method "integrated_gradients", values = the IG map, and metadata recording steps and target index used.

The documentation for this class was generated from the following file:

include/pulsatrix/integrated_gradients.hpp

Public Member Functions

Detailed Description

Member Function Documentation

◆ explain()