Class GoogleCloudMlV1ExplanationConfig
Message holding configuration options for explaining model predictions. There are three feature attribution methods supported for TensorFlow models: integrated gradients, sampled Shapley, and XRAI. Learn more about feature attributions.
Implements
Inherited Members
Namespace: Google.Apis.CloudMachineLearningEngine.v1.Data
Assembly: Google.Apis.CloudMachineLearningEngine.v1.dll
Syntax
public class GoogleCloudMlV1ExplanationConfig : IDirectResponseSchema
Properties
ETag
The ETag of the item.
Declaration
public virtual string ETag { get; set; }
Property Value
Type | Description |
---|---|
string |
IntegratedGradientsAttribution
Attributes credit by computing 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
Declaration
[JsonProperty("integratedGradientsAttribution")]
public virtual GoogleCloudMlV1IntegratedGradientsAttribution IntegratedGradientsAttribution { get; set; }
Property Value
Type | Description |
---|---|
GoogleCloudMlV1IntegratedGradientsAttribution |
SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
Declaration
[JsonProperty("sampledShapleyAttribution")]
public virtual GoogleCloudMlV1SampledShapleyAttribution SampledShapleyAttribution { get; set; }
Property Value
Type | Description |
---|---|
GoogleCloudMlV1SampledShapleyAttribution |
XraiAttribution
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
Declaration
[JsonProperty("xraiAttribution")]
public virtual GoogleCloudMlV1XraiAttribution XraiAttribution { get; set; }
Property Value
Type | Description |
---|---|
GoogleCloudMlV1XraiAttribution |