Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges

TL;DR

This paper reviews explanation methods in deep learning, analyzing user concerns, legal considerations, and challenges, highlighting the gap in explanations for lay users and addressing issues of bias and fairness.

Contribution

It introduces a taxonomy of explanation methods, analyzes user concerns, and discusses the challenges in providing explanations suitable for lay users in deep neural networks.

Findings

Visual explanations about input influence are possible.

Explanation methods for lay users are lacking.

Bias and fairness issues remain difficult to address.

Abstract

Issues regarding explainable AI involve four components: users, laws & regulations, explanations and algorithms. Together these components provide a context in which explanation methods can be evaluated regarding their adequacy. The goal of this chapter is to bridge the gap between expert users and lay users. Different kinds of users are identified and their concerns revealed, relevant statements from the General Data Protection Regulation are analyzed in the context of Deep Neural Networks (DNNs), a taxonomy for the classification of existing explanation methods is introduced, and finally, the various classes of explanation methods are analyzed to verify if user concerns are justified. Overall, it is clear that (visual) explanations can be given about various aspects of the influence of the input on the output. However, it is noted that explanation methods or interfaces for lay users are missing and we speculate which criteria these methods / interfaces should satisfy. Finally it is noted that two important concerns are difficult to address with explanation methods: the concern about bias in datasets that leads to biased DNNs, as well as the suspicion about unfair outcomes.