PhilSci Archive

Robustness in Machine Learning Explanations: Does It Matter?

Hancox-Li, Leif (2020) Robustness in Machine Learning Explanations: Does It Matter? [Preprint]

WarningThere is a more recent version of this item available.
[img]
Preview
Text
sample-authordraft.pdf

Download (452kB) | Preview

Abstract

The explainable AI literature contains multiple notions of what an explanation is and what desiderata explanations should satisfy. One implicit source of disagreement is how far the explanations should reflect real patterns in the data or the world. This disagreement underlies debates about other desiderata, such as how robust explanations are to slight perturbations in the input data. I argue that robustness is desirable to the extent that we’re concerned about finding real patterns in the world. The import of real patterns differs according to the problem context. In some contexts, non-robust explanations can constitute a moral hazard. By being clear about the extent to which we care about capturing real patterns, we can also determine whether the Rashomon Effect is a boon or a bane.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Hancox-Li, Leifdidine@gmail.com
Keywords: explanation, philosophy, epistemology, machine learning, objectivity, robustness, arti cial intelligence, methodology, ethics
Subjects: General Issues > Ethical Issues
General Issues > Explanation
General Issues > Formal Learning Theory
General Issues > Science and Society
General Issues > Technology
Depositing User: Leif Hancox-Li
Date Deposited: 08 Dec 2019 03:24
Last Modified: 08 Dec 2019 03:24
Item ID: 16686
DOI or Unique Handle: 10.1145/3351095.3372836
Subjects: General Issues > Ethical Issues
General Issues > Explanation
General Issues > Formal Learning Theory
General Issues > Science and Society
General Issues > Technology
Date: 2020
URI: http://philsci-archive.pitt.edu/id/eprint/16686

Available Versions of this Item

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Altmetric.com

Actions (login required)

View Item View Item