Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

11/15/2020
by   Umang Bhatt, et al.
6

Transparency of algorithmic systems entails exposing system properties to various stakeholders for purposes that include understanding, improving, and/or contesting predictions. The machine learning (ML) community has mostly considered explainability as a proxy for transparency. With this work, we seek to encourage researchers to study uncertainty as a form of transparency and practitioners to communicate uncertainty estimates to stakeholders. First, we discuss methods for assessing uncertainty. Then, we describe the utility of uncertainty for mitigating model unfairness, augmenting decision-making, and building trustworthy systems. We also review methods for displaying uncertainty to stakeholders and discuss how to collect information required for incorporating uncertainty into existing ML pipelines. Our contribution is an interdisciplinary review to inform how to measure, communicate, and use uncertainty as a form of transparency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/09/2019

Transparency in Maintenance of Recruitment Chatbots

We report on experiences with implementing conversational agents in the ...
research
11/09/2022

Accountable and Explainable Methods for Complex Reasoning over Text

A major concern of Machine Learning (ML) models is their opacity. They a...
research
04/02/2020

Best Practices for Transparency in Machine Generated Personalization

Machine generated personalization is increasingly used in online systems...
research
04/27/2022

Prescriptive and Descriptive Approaches to Machine-Learning Transparency

Specialized documentation techniques have been developed to communicate ...
research
10/12/2022

Quantifying Uncertainty with Probabilistic Machine Learning Modeling in Wireless Sensing

The application of machine learning (ML) techniques in wireless communic...
research
03/27/2021

A Multistakeholder Approach Towards Evaluating AI Transparency Mechanisms

Given that there are a variety of stakeholders involved in, and affected...
research
10/01/2018

Utilizing a Transparency-driven Environment toward Trusted Automatic Genre Classification: A Case Study in Journalism History

With the growing abundance of unlabeled data in real-world tasks, resear...

Please sign up or login with your details

Forgot password? Click here to reset