Class IntegratedGradientsAttribution (1.3.0) 

public sealed class IntegratedGradientsAttribution : IMessage<IntegratedGradientsAttribution>, IEquatable<IntegratedGradientsAttribution>, IDeepCloneable<IntegratedGradientsAttribution>, IBufferMessage, IMessage

An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

Inheritance

Object > IntegratedGradientsAttribution

Namespace

Google.Cloud.AIPlatform.V1

Assembly

Google.Cloud.AIPlatform.V1.dll

Constructors

IntegratedGradientsAttribution()

public IntegratedGradientsAttribution()

IntegratedGradientsAttribution(IntegratedGradientsAttribution)

public IntegratedGradientsAttribution(IntegratedGradientsAttribution other)
Parameter
NameDescription
otherIntegratedGradientsAttribution

Properties

BlurBaselineConfig

public BlurBaselineConfig BlurBaselineConfig { get; set; }

Config for IG with blur baseline.

When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383

Property Value
TypeDescription
BlurBaselineConfig

SmoothGradConfig

public SmoothGradConfig SmoothGradConfig { get; set; }

Config for SmoothGrad approximation of gradients.

When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf

Property Value
TypeDescription
SmoothGradConfig

StepCount

public int StepCount { get; set; }

Required. The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range.

Valid range of its value is [1, 100], inclusively.

Property Value
TypeDescription
Int32