Header

UZH-Logo

Maintenance Infos

Transparency as design publicity: explaining and justifying inscrutable algorithms


Loi, Michele; Ferrario, Andrea; Viganò, Eleonora (2020). Transparency as design publicity: explaining and justifying inscrutable algorithms. Ethics and Information Technology:Epub ahead of print.

Abstract

In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions (post-hoc) interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in explaining algorithms as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance) in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand (the demand for impersonal justification) of the explainee. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.

Abstract

In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions (post-hoc) interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in explaining algorithms as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance) in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand (the demand for impersonal justification) of the explainee. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.

Statistics

Citations

Altmetrics

Downloads

4 downloads since deposited on 05 Feb 2021
4 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > Institute of Biomedical Ethics and History of Medicine
Dewey Decimal Classification:610 Medicine & health
Scopus Subject Areas:Physical Sciences > Computer Science Applications
Social Sciences & Humanities > Library and Information Sciences
Uncontrolled Keywords:Library and Information Sciences, Computer Science Applications
Language:English
Date:20 October 2020
Deposited On:05 Feb 2021 16:47
Last Modified:06 Feb 2021 21:03
Publisher:Springer
ISSN:1388-1957
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1007/s10676-020-09564-w
Related URLs:https://www.zora.uzh.ch/id/eprint/177144/
Project Information:
  • : FunderH2020
  • : Grant ID700540
  • : Project TitleCANVAS - Constructing an Alliance for Value-driven Cybersecurity
  • : FunderSERI
  • : Grant ID16.0052-1
  • : Project TitleSwiss State Secretariat for Education, Research and Innovation
  • : FunderNRP 75
  • : Grant ID407540_167218
  • : Project TitleNational Research Programme 75 "Big Data"

Download

Hybrid Open Access

Download PDF  'Transparency as design publicity: explaining and justifying inscrutable algorithms'.
Preview
Content: Published Version
Filetype: PDF
Size: 608kB
View at publisher
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)