Explainable AI for BigQuery ML models

Explainable AI is a suite of techniques you can use to understand the predictions and decisions of your AI models. BigQuery ML and Vertex AI both have existing Explainable AI offerings which offer feature-based explanations.

Use this page to understand if you can use Explainable AI on BigQuery ML models that registered with the Model Registry.

BigQuery ML itself supports Explainable AI on two separate frameworks, and therefore supports different model types. This page describes what model types are supported for the Model Registry integration. To learn about BigQuery ML based Explainable AI, see Performing XAI on models in BigQuery ML.

Supported model types for Explainable AI in Vertex AI

Explainable AI is available in Vertex AI for a subset of exportable supervised learning models. Model types that are not in the following list might support Explainable AI if you manually edit their metadata. For more details, see Introduction to Vertex Explainable AI.

Model type Explainable AI method
dnn_classifier Integrated gradients
dnn_regressor Integrated gradients
dnn_linear_combined_classifier Integrated gradients
dnn_linear_combined_regressor Integrated gradients
boosted_tree_regressor Sampled shapley
boosted_tree_classifier Sampled shapley
random_forest_regressor Sampled shapley
random_forest_classifier Sampled shapley

See Feature Attribution Methods to learn more about these methods.

Enable Explainable AI in Model Registry

When your BigQuery ML model is registered in Model Registry, and if it is an Explainable AI supported model type, you can enable Explainable AI on the model when deploying to an endpoint. When you register your BigQuery ML model, all of the associated metadata is populated for you.

  1. Register your BigQuery ML model to the Model Registry.
  2. Go to the Model Registry page from the BigQuery section in the Google Cloud console.
  3. From the Model Registry, select the BigQuery ML model and click the model version to redirect to the model detail page.
  4. Select More actions from the model version.
  5. Click Deploy to endpoint.
  6. Define your endpoint - create an endpoint name and click continue.
  7. Select a machine type, for example, n1-standard-2.
  8. Under Model settings, in the logging section, Select the checkbox to enable Explainability options.
  9. Click Done, and then Continue to deploy to the endpoint.

Enable XAI from console

To learn how to use XAI on your models from the Model Registry, see Get an online explanation using your deployed model. To learn more about XAI in Vertex AI, see Get explanations.

Learn more