DAX: deep argumentative eXplanation for neural networks
OA Location
Author(s)
Albini, Emanuele
Lertvittayakumjorn, Piyawat
Rago, Antonio
Toni, Francesca
Type
Working Paper
Abstract
Despite the rapid growth in attention on eXplainable AI (XAI) of late,
explanations in the literature provide little insight into the actual
functioning of Neural Networks (NNs), significantly limiting their
transparency. We propose a methodology for explaining NNs, providing
transparency about their inner workings, by utilising computational
argumentation (a form of symbolic AI offering reasoning abstractions for a
variety of settings where opinions matter) as the scaffolding underpinning Deep
Argumentative eXplanations (DAXs). We define three DAX instantiations (for
various neural architectures and tasks) and evaluate them empirically in terms
of stability, computational cost, and importance of depth. We also conduct
human experiments with DAXs for text classification models, indicating that
they are comprehensible to humans and align with their judgement, while also
being competitive, in terms of user acceptance, with existing approaches to XAI
that also have an argumentative spirit.
explanations in the literature provide little insight into the actual
functioning of Neural Networks (NNs), significantly limiting their
transparency. We propose a methodology for explaining NNs, providing
transparency about their inner workings, by utilising computational
argumentation (a form of symbolic AI offering reasoning abstractions for a
variety of settings where opinions matter) as the scaffolding underpinning Deep
Argumentative eXplanations (DAXs). We define three DAX instantiations (for
various neural architectures and tasks) and evaluate them empirically in terms
of stability, computational cost, and importance of depth. We also conduct
human experiments with DAXs for text classification models, indicating that
they are comprehensible to humans and align with their judgement, while also
being competitive, in terms of user acceptance, with existing approaches to XAI
that also have an argumentative spirit.
Date Issued
2021-03-01
Citation
2021
Publisher
arXiv
Copyright Statement
© 2021 The Author(s)
Sponsor
Royal Academy Of Engineering
Identifier
http://arxiv.org/abs/2012.05766v2
Grant Number
RCSRF2021\11\45
Subjects
cs.AI
cs.AI
Notes
19 pages, 15 figures
Publication Status
Published