Prescriptive and Descriptive Approaches to Machine-Learning Transparency

TL;DR

This paper reviews descriptive documentation methods for ML systems and introduces Method Cards, a prescriptive approach to guide ML engineers in improving and troubleshooting models.

Contribution

It proposes Method Cards as a new prescriptive documentation tool to enhance ML transparency and reproducibility, complementing existing descriptive techniques.

Findings

Method Cards effectively communicate key considerations for model development.

They improve transparency and reproducibility in ML systems.

Example application in small object detection demonstrates practical utility.

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 have taken a mainly descriptive approach, providing various details about the system components. While the above information is essential for product developers and external experts to assess whether the ML system meets their requirements, other stakeholders might find it less actionable. In particular, ML engineers need guidance on how to mitigate potential shortcomings in order to fix bugs or improve the system's performance. We survey approaches that aim to provide such guidance in a prescriptive way. We further propose a preliminary approach, called Method Cards, which aims to increase the transparency and reproducibility of ML systems by providing prescriptive documentation of commonly-used ML methods and techniques. We showcase our proposal with an example in small object detection, and demonstrate how Method Cards can communicate key considerations for model developers. We further highlight avenues for improving the user experience of ML engineers based on Method Cards.