Connect with us

Amazon

New ML Governance Tools for Amazon SageMaker – Simplify Access Control and Enhance Transparency Over Your ML Projects

As companies increasingly adopt machine learning (ML) for their business applications, they are looking for ways to improve governance of their ML projects with simplified access control and enhanced visibility across the ML lifecycle. A common challenge in that effort is managing the right set of user permissions across different groups and ML activities. For…

Published

on

Voiced by Polly

As companies increasingly adopt machine learning (ML) for their business applications, they are looking for ways to improve governance of their ML projects with simplified access control and enhanced visibility across the ML lifecycle. A common challenge in that effort is managing the right set of user permissions across different groups and ML activities. For example, a data scientist in your team that builds and trains models usually requires different permissions than an MLOps engineer that manages ML pipelines. Another challenge is improving visibility over ML projects. For example, model information, such as intended use, out-of-scope use cases, risk rating, and evaluation results, is often captured and shared via emails or documents. In addition, there is often no simple mechanism to monitor and report on your deployed model behavior.

That’s why I’m excited to announce a new set of ML governance tools for Amazon SageMaker.

As an ML system or platform administrator, you can now use Amazon SageMaker Role Manager to define custom permissions for SageMaker users in minutes, so you can onboard users faster. As an ML practitioner, business owner, or model risk and compliance officer, you can now use Amazon SageMaker Model Cards to document model information from conception to deployment and Amazon SageMaker Model Dashboard to monitor all your deployed models through a unified dashboard.

Let’s dive deeper into each tool, and I’ll show you how to get started.

Introducing Amazon SageMaker Role Manager
SageMaker Role Manager lets you define custom permissions for SageMaker users in minutes. It comes with a set of predefined policy templates for different personas and ML activities. Personas represent the different types of users that need permissions to perform ML activities in SageMaker, such as data scientists or MLOps engineers. ML activities are a set of permissions to accomplish a common ML task, such as running SageMaker Studio applications or managing experiments, models, or pipelines. You can also define additional personas, add ML activities, and your managed policies to match your specific needs. Once you have selected the persona type and the set of ML activities, SageMaker Role Manager automatically creates the required AWS Identity and Access Management (IAM) role and policies that you can assign to SageMaker users.

A Primer on SageMaker and IAM Roles
A role is an IAM identity that has permissions to perform actions with AWS services. Besides user roles that are assumed by a user via federation from an Identity Provider (IdP) or the AWS Console, Amazon SageMaker requires service roles (also known as execution roles) to perform actions on behalf of the user. SageMaker Role Manager helps you create these service roles:

  • SageMaker Compute Role – Gives SageMaker compute resources the ability to perform tasks such as training and inference, typically used via PassRole. You can select the SageMaker Compute Role persona in SageMaker Role Manager to create this role. Depending on the ML activities you select in your SageMaker service roles, you will need to create this compute role first.
  • SageMaker Service Role – Some AWS services, including SageMaker, require a service role to perform actions on your behalf. You can select the Data Scientist, MLOps, or Custom persona in SageMaker Role Manager to start creating service roles with custom permissions for your ML practitioners.

Now, let me show you how this works in practice.

There are two ways to get to SageMaker Role Manager, either through Getting started in the SageMaker console or when you select Add user in the SageMaker Studio Domain control panel.

I start in the SageMaker console. Under Configure role, select Create a role. This opens a workflow that guides you through all required steps.

Amazon SageMaker Admin Hub - Getting Started

Let’s assume I want to create a SageMaker service role with a specific set of permissions for my team of data scientists. In Step 1, I select the predefined policy template for the Data Scientist persona.

Amazon SageMaker Role Manager - Select persona

I can also define the network and encryption settings in this step by selecting Amazon Virtual Private Cloud (Amazon VPC) subnets, security groups, and encryption keys.

In Step 2, I select what ML activities data scientists in my team need to perform.

Amazon SageMaker Admin Hub - Configure ML activities

Some of the selected ML activities might require you to specify the Amazon Resource Name (ARN) of the SageMaker Compute Role so SageMaker compute resources have the ability to perform the tasks.

In Step 3, you can attach additional IAM policies and add tags to the role if needed. Tags help you identify and organize your AWS resources. You can use tags to add attributes such as project name, cost center, or location information to a role. After a final review of the settings in Step 4, select Submit, and the role is created.

In just a few minutes, I set up a SageMaker service role, and I’m now ready to onboard data scientists in SageMaker with custom permissions in place.

Introducing Amazon SageMaker Model Cards
SageMaker Model Cards helps you streamline model documentation throughout the ML lifecycle by creating a single source of truth for model information. For models trained on SageMaker, SageMaker Model Cards discovers and autopopulates details such as training jobs, training datasets, model artifacts, and inference environment. You can also record model details such as the model’s intended use, risk rating, and evaluation results. For compliance documentation and model evidence reporting, you can export your model cards to a PDF file and easily share them with your customers or regulators.

To start creating SageMaker Model Cards, go to the SageMaker console, select Governance in the left navigation menu, and select Model cards.

Amazon SageMaker Model Cards

Select Create model card to document your model information.

Amazon SageMaker Model Card

Amazon SageMaker Model Cards

Introducing Amazon SageMaker Model Dashboard
SageMaker Model Dashboard lets you monitor all your models in one place. With this bird’s-eye view, you can now see which models are used in production, view model cards, visualize model lineage, track resources, and monitor model behavior through an integration with SageMaker Model Monitor and SageMaker Clarify. The dashboard automatically alerts you when models are not being monitored or deviate from expected behavior. You can also drill deeper into individual models to troubleshoot issues.

To access SageMaker Model Dashboard, go to the SageMaker console, select Governance in the left navigation menu, and select Model dashboard.

Amazon SageMaker Model Dashboard

Note: The risk rating shown above is for illustrative purposes only and may vary based on input provided by you.

Now Available
Amazon SageMaker Role Manager, SageMaker Model Cards, and SageMaker Model Dashboard are available today at no additional charge in all the AWS Regions where Amazon SageMaker is available except for the AWS GovCloud and AWS China Regions.

To learn more, visit ML governance with Amazon SageMaker and check the developer guide.

Start building your ML projects with our new governance tools for Amazon SageMaker today

— Antje



Source

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Amazon

Create your fashion assistant application using Amazon Titan models and Amazon Bedrock Agents

In this post, we implement a fashion assistant agent using Amazon Bedrock Agents and the Amazon Titan family models. The fashion assistant provides a personalized, multimodal conversational experience. Source

Published

on

By

In this post, we implement a fashion assistant agent using Amazon Bedrock Agents and the Amazon Titan family models. The fashion assistant provides a personalized, multimodal conversational experience.

Source

Continue Reading

Amazon

Implement model-independent safety measures with Amazon Bedrock Guardrails

In this post, we discuss how you can use the ApplyGuardrail API in common generative AI architectures such as third-party or self-hosted large language models (LLMs), or in a self-managed Retrieval Augmented Generation (RAG) architecture. Source

Published

on

By

In this post, we discuss how you can use the ApplyGuardrail API in common generative AI architectures such as third-party or self-hosted large language models (LLMs), or in a self-managed Retrieval Augmented Generation (RAG) architecture.

Source

Continue Reading

Amazon

Visier’s data science team boosts their model output 10 times by migrating to Amazon SageMaker

In this post, we learn how Visier was able to boost their model output by 10 times, accelerate innovation cycles, and unlock new opportunities using Amazon SageMaker. Source

Published

on

By

In this post, we learn how Visier was able to boost their model output by 10 times, accelerate innovation cycles, and unlock new opportunities using Amazon SageMaker.

Source

Continue Reading

Trending

Copyright © 2021 Today's Digital.