public sealed class IntegratedGradientsAttribution : IMessage<IntegratedGradientsAttribution>, IEquatable<IntegratedGradientsAttribution>, IDeepCloneable<IntegratedGradientsAttribution>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class IntegratedGradientsAttribution.
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
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
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
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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-28 UTC."],[[["\u003cp\u003e\u003ccode\u003eIntegratedGradientsAttribution\u003c/code\u003e is a class in the Vertex AI v1beta1 API for calculating Aumann-Shapley values, leveraging the model's differentiable structure as detailed in the linked research paper.\u003c/p\u003e\n"],["\u003cp\u003eThis class inherits from \u003ccode\u003eobject\u003c/code\u003e and implements several interfaces including \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e within the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1Beta1\u003c/code\u003e namespace, and is contained in the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1Beta1.dll\u003c/code\u003e assembly.\u003c/p\u003e\n"],["\u003cp\u003eThe class includes constructors for creating instances, both with default settings and by copying another \u003ccode\u003eIntegratedGradientsAttribution\u003c/code\u003e object, as well as properties for configuring \u003ccode\u003eBlurBaselineConfig\u003c/code\u003e and \u003ccode\u003eSmoothGradConfig\u003c/code\u003e to enhance attribution methods.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eStepCount\u003c/code\u003e property, which is a required integer, determines the precision of path integral approximation, with a recommended starting value of 50, and is bounded within the range of 1 to 100.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class IntegratedGradientsAttribution (1.0.0-beta47)\n\nVersion latestkeyboard_arrow_down\n\n- [1.0.0-beta47 (latest)](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.IntegratedGradientsAttribution)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.IntegratedGradientsAttribution) \n\n public sealed class IntegratedGradientsAttribution : IMessage\u003cIntegratedGradientsAttribution\u003e, IEquatable\u003cIntegratedGradientsAttribution\u003e, IDeepCloneable\u003cIntegratedGradientsAttribution\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class IntegratedGradientsAttribution.\n\nAn attribution method that computes the Aumann-Shapley value taking advantage\nof the model's fully differentiable structure. Refer to this paper for\nmore details: \u003chttps://arxiv.org/abs/1703.01365\u003e \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e IntegratedGradientsAttribution \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[IntegratedGradientsAttribution](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.IntegratedGradientsAttribution), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[IntegratedGradientsAttribution](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.IntegratedGradientsAttribution), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[IntegratedGradientsAttribution](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.IntegratedGradientsAttribution), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.AIPlatform.V1Beta1](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.AIPlatform.V1Beta1.dll\n\nConstructors\n------------\n\n### IntegratedGradientsAttribution()\n\n public IntegratedGradientsAttribution()\n\n### IntegratedGradientsAttribution(IntegratedGradientsAttribution)\n\n public IntegratedGradientsAttribution(IntegratedGradientsAttribution other)\n\nProperties\n----------\n\n### BlurBaselineConfig\n\n public BlurBaselineConfig BlurBaselineConfig { get; set; }\n\nConfig for IG with blur baseline.\n\nWhen enabled, a linear path from the maximally blurred image to the input\nimage is created. Using a blurred baseline instead of zero (black image) is\nmotivated by the BlurIG approach explained here:\n\u003chttps://arxiv.org/abs/2004.03383\u003e\n\n### SmoothGradConfig\n\n public SmoothGradConfig SmoothGradConfig { get; set; }\n\nConfig for SmoothGrad approximation of gradients.\n\nWhen enabled, the gradients are approximated by averaging the gradients\nfrom noisy samples in the vicinity of the inputs. Adding\nnoise can help improve the computed gradients. Refer to this paper for more\ndetails: \u003chttps://arxiv.org/pdf/1706.03825.pdf\u003e\n\n### StepCount\n\n public int StepCount { get; set; }\n\nRequired. The number of steps for approximating the path integral.\nA good value to start is 50 and gradually increase until the\nsum to diff property is within the desired error range.\n\nValid range of its value is \\[1, 100\\], inclusively."]]
