System-Level Transparency of Machine Learning

February 22, 2022

Abstract

Specialized documentation techniques have been developed to communicate key facts about machine-learning (ML) systems and the datasets and models they rely on. Techniques such as Datasheets, FactSheets, and Model Cards began the journey towards model documentation that provides ML explainability and transparency. Our proposal, called System Cards, aims to increase the transparency of ML systems by providing stakeholders with an overview of different components of an ML system, how these components interact, and how different pieces of data and protected information are used by the system.

Download the Paper

AUTHORS

Written by

Bilal Alsallakh

Adeel Cheema

Chavez Procope

David Adkins

Emily McReynolds

Erin Wang

Grace Pehl

Nekesha Green

Polina Zvyagina

Publisher

Meta AI