Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Output only. Aggregated attributions explaining the Model's prediction
outputs over the set of instances. The attributions are grouped by outputs.
For Models that predict only one output, such as regression Models that
predict only one score, there is only one attibution that explains the
predicted output. For Models that predict multiple outputs, such as
multiclass Models that predict multiple classes, each element explains one
specific item.
Attribution.output_index
can be used to identify which output this attribution is explaining.
The
baselineOutputValue,
instanceOutputValue
and
featureAttributions
fields are averaged over the test data.
NOTE: Currently AutoML tabular classification Models produce only one
attribution, which averages attributions over all the classes it predicts.
Attribution.approximation_error
is not populated.
Output only. Aggregated attributions explaining the Model's prediction
outputs over the set of instances. The attributions are grouped by outputs.
For Models that predict only one output, such as regression Models that
predict only one score, there is only one attibution that explains the
predicted output. For Models that predict multiple outputs, such as
multiclass Models that predict multiple classes, each element explains one
specific item.
Attribution.output_index
can be used to identify which output this attribution is explaining.
The
baselineOutputValue,
instanceOutputValue
and
featureAttributions
fields are averaged over the test data.
NOTE: Currently AutoML tabular classification Models produce only one
attribution, which averages attributions over all the classes it predicts.
Attribution.approximation_error
is not populated.
Output only. Aggregated attributions explaining the Model's prediction
outputs over the set of instances. The attributions are grouped by outputs.
For Models that predict only one output, such as regression Models that
predict only one score, there is only one attibution that explains the
predicted output. For Models that predict multiple outputs, such as
multiclass Models that predict multiple classes, each element explains one
specific item.
Attribution.output_index
can be used to identify which output this attribution is explaining.
The
baselineOutputValue,
instanceOutputValue
and
featureAttributions
fields are averaged over the test data.
NOTE: Currently AutoML tabular classification Models produce only one
attribution, which averages attributions over all the classes it predicts.
Attribution.approximation_error
is not populated.
Output only. Aggregated attributions explaining the Model's prediction
outputs over the set of instances. The attributions are grouped by outputs.
For Models that predict only one output, such as regression Models that
predict only one score, there is only one attibution that explains the
predicted output. For Models that predict multiple outputs, such as
multiclass Models that predict multiple classes, each element explains one
specific item.
Attribution.output_index
can be used to identify which output this attribution is explaining.
The
baselineOutputValue,
instanceOutputValue
and
featureAttributions
fields are averaged over the test data.
NOTE: Currently AutoML tabular classification Models produce only one
attribution, which averages attributions over all the classes it predicts.
Attribution.approximation_error
is not populated.
Output only. Aggregated attributions explaining the Model's prediction
outputs over the set of instances. The attributions are grouped by outputs.
For Models that predict only one output, such as regression Models that
predict only one score, there is only one attibution that explains the
predicted output. For Models that predict multiple outputs, such as
multiclass Models that predict multiple classes, each element explains one
specific item.
Attribution.output_index
can be used to identify which output this attribution is explaining.
The
baselineOutputValue,
instanceOutputValue
and
featureAttributions
fields are averaged over the test data.
NOTE: Currently AutoML tabular classification Models produce only one
attribution, which averages attributions over all the classes it predicts.
Attribution.approximation_error
is not populated.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Interface ModelExplanationOrBuilder (1.32.0)\n\n public interface ModelExplanationOrBuilder extends MessageOrBuilder\n\nImplements\n----------\n\n[MessageOrBuilder](https://cloud.google.com/java/docs/reference/protobuf/latest/com.google.protobuf.MessageOrBuilder.html)\n\nMethods\n-------\n\n### getMeanAttributions(int index)\n\n public abstract Attribution getMeanAttributions(int index)\n\nOutput only. Aggregated attributions explaining the Model's prediction\noutputs over the set of instances. The attributions are grouped by outputs.\n\nFor Models that predict only one output, such as regression Models that\npredict only one score, there is only one attibution that explains the\npredicted output. For Models that predict multiple outputs, such as\nmulticlass Models that predict multiple classes, each element explains one\nspecific item.\nAttribution.output_index\ncan be used to identify which output this attribution is explaining.\n\nThe\nbaselineOutputValue,\ninstanceOutputValue\nand\nfeatureAttributions\nfields are averaged over the test data.\n\nNOTE: Currently AutoML tabular classification Models produce only one\nattribution, which averages attributions over all the classes it predicts.\nAttribution.approximation_error\nis not populated.\n\n`\nrepeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];\n`\n\n### getMeanAttributionsCount()\n\n public abstract int getMeanAttributionsCount()\n\nOutput only. Aggregated attributions explaining the Model's prediction\noutputs over the set of instances. The attributions are grouped by outputs.\n\nFor Models that predict only one output, such as regression Models that\npredict only one score, there is only one attibution that explains the\npredicted output. For Models that predict multiple outputs, such as\nmulticlass Models that predict multiple classes, each element explains one\nspecific item.\nAttribution.output_index\ncan be used to identify which output this attribution is explaining.\n\nThe\nbaselineOutputValue,\ninstanceOutputValue\nand\nfeatureAttributions\nfields are averaged over the test data.\n\nNOTE: Currently AutoML tabular classification Models produce only one\nattribution, which averages attributions over all the classes it predicts.\nAttribution.approximation_error\nis not populated.\n\n`\nrepeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];\n`\n\n### getMeanAttributionsList()\n\n public abstract List\u003cAttribution\u003e getMeanAttributionsList()\n\nOutput only. Aggregated attributions explaining the Model's prediction\noutputs over the set of instances. The attributions are grouped by outputs.\n\nFor Models that predict only one output, such as regression Models that\npredict only one score, there is only one attibution that explains the\npredicted output. For Models that predict multiple outputs, such as\nmulticlass Models that predict multiple classes, each element explains one\nspecific item.\nAttribution.output_index\ncan be used to identify which output this attribution is explaining.\n\nThe\nbaselineOutputValue,\ninstanceOutputValue\nand\nfeatureAttributions\nfields are averaged over the test data.\n\nNOTE: Currently AutoML tabular classification Models produce only one\nattribution, which averages attributions over all the classes it predicts.\nAttribution.approximation_error\nis not populated.\n\n`\nrepeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];\n`\n\n### getMeanAttributionsOrBuilder(int index)\n\n public abstract AttributionOrBuilder getMeanAttributionsOrBuilder(int index)\n\nOutput only. Aggregated attributions explaining the Model's prediction\noutputs over the set of instances. The attributions are grouped by outputs.\n\nFor Models that predict only one output, such as regression Models that\npredict only one score, there is only one attibution that explains the\npredicted output. For Models that predict multiple outputs, such as\nmulticlass Models that predict multiple classes, each element explains one\nspecific item.\nAttribution.output_index\ncan be used to identify which output this attribution is explaining.\n\nThe\nbaselineOutputValue,\ninstanceOutputValue\nand\nfeatureAttributions\nfields are averaged over the test data.\n\nNOTE: Currently AutoML tabular classification Models produce only one\nattribution, which averages attributions over all the classes it predicts.\nAttribution.approximation_error\nis not populated.\n\n`\nrepeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];\n`\n\n### getMeanAttributionsOrBuilderList()\n\n public abstract List\u003c? extends AttributionOrBuilder\u003e getMeanAttributionsOrBuilderList()\n\nOutput only. Aggregated attributions explaining the Model's prediction\noutputs over the set of instances. The attributions are grouped by outputs.\n\nFor Models that predict only one output, such as regression Models that\npredict only one score, there is only one attibution that explains the\npredicted output. For Models that predict multiple outputs, such as\nmulticlass Models that predict multiple classes, each element explains one\nspecific item.\nAttribution.output_index\ncan be used to identify which output this attribution is explaining.\n\nThe\nbaselineOutputValue,\ninstanceOutputValue\nand\nfeatureAttributions\nfields are averaged over the test data.\n\nNOTE: Currently AutoML tabular classification Models produce only one\nattribution, which averages attributions over all the classes it predicts.\nAttribution.approximation_error\nis not populated.\n\n`\nrepeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];\n`"]]