Algorithm |
Type |
Description |
---|---|---|
Integrated Gradients |
Gradient |
Approximates the integral of gradients along the path (straight line from baseline to input) and multiplies with (input - baseline) |
DeepLift |
Application |
Explains differences in the non-linear activations' outputs in terms of the differences of the input from its corresponding reference. NOTE: Currently, only rescale rule is supported. |
GradientSHAP |
Gradient |
Approximates SHAP values based on the expected gradients. It adds gaussian noise to each input example #samples times, selects a random point between each sample and randomly drawn baseline from baselines' distribution, computes the gradient for it and multiples it with (input - baseline). Final SHAP values represent the expected values of gradients * (input - baseline) for each input example. |
Layer Conductance |
Gradient |
Decomposes integrated gradients via chain rule. It approximates the integral of gradients defined by a chain rule, described as the gradients of the output w.r.t. to the neurons multiplied by the gradients of the neurons w.r.t. the inputs, along the path from baseline to inputs. Finally, the latter is multiplied by (input - baseline). |