CUED Publications database

Explainable Machine Learning in Deployment

Bhatt, U and Xiang, A and Sharma, S and Weller, A and Taly, A and Jia, Y and Ghosh, J and Puri, R and Moura, JMF and Eckersley, P Explainable Machine Learning in Deployment. (Unpublished)

Full text not available from this repository.


Explainable machine learning offers the potential to provide stakeholders with insights into model behavior by using various methods such as feature importance scores, counterfactual explanations, or influential training data. Yet there is little understanding of how organizations use these methods in practice. This study explores how organizations view and use explainability for stakeholder consumption. We find that, currently, the majority of deployments are not for end users affected by the model but rather for machine learning engineers, who use explainability to debug the model itself. There is thus a gap between explainability in practice and the goal of transparency, since explanations primarily serve internal stakeholders rather than external ones. Our study synthesizes the limitations of current explainability techniques that hamper their use for end users. To facilitate end user interaction, we develop a framework for establishing clear goals for explainability. We end by discussing concerns raised regarding explainability.

Item Type: Article
Uncontrolled Keywords: cs.LG cs.LG cs.AI cs.CY cs.HC stat.ML
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 19 Sep 2019 03:07
Last Modified: 18 Feb 2021 18:14