Argflow: a toolkit for deep argumentative explanations for neural networks
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
In recent years, machine learning (ML) models have been successfully applied in a variety of real-world applications. However, they
are often complex and incomprehensible to human users. This can
decrease trust in their outputs and render their usage in critical
settings ethically problematic. As a result, several methods for explaining such ML models have been proposed recently, in particular
for black-box models such as deep neural networks (NNs). Nevertheless, these methods predominantly explain outputs in terms
of inputs, disregarding the inner workings of the ML model computing those outputs. We present Argflow, a toolkit enabling the
generation of a variety of ‘deep’ argumentative explanations (DAXs)
for outputs of NNs on classification tasks.
are often complex and incomprehensible to human users. This can
decrease trust in their outputs and render their usage in critical
settings ethically problematic. As a result, several methods for explaining such ML models have been proposed recently, in particular
for black-box models such as deep neural networks (NNs). Nevertheless, these methods predominantly explain outputs in terms
of inputs, disregarding the inner workings of the ML model computing those outputs. We present Argflow, a toolkit enabling the
generation of a variety of ‘deep’ argumentative explanations (DAXs)
for outputs of NNs on classification tasks.
Editor(s)
Dignum, Frank
Lomuscio, Alessio
Endriss, Ulle
Nowé, Ann
Date Issued
2021-05-03
Date Acceptance
2021-05-03
Citation
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 2021, 3, pp.1761-1763
ISBN
978-1-4503-8307-3
ISSN
1558-2914
Start Page
1761
End Page
1763
Journal / Book Title
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume
3
Copyright Statement
Copyright © ACM 2021. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, https://dl.acm.org/doi/10.5555/3463952.3464229
Identifier
https://dl.acm.org/doi/proceedings/10.5555/3463952?tocHeading=heading1
Source
Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems
Publication Status
Published
Start Date
2021-05-03
Finish Date
2021-05-07
Coverage Spatial
Online