Influence-driven explanations for bayesian network classifiers
OA Location
Author(s)
Rago, Antonio
Albini, Emanuele
Baroni, Pietro
Toni, Francesca
Type
Working Paper
Abstract
One of the most pressing issues in AI in recent years has been the need to
address the lack of explainability of many of its models. We focus on
explanations for discrete Bayesian network classifiers (BCs), targeting greater
transparency of their inner workings by including intermediate variables in
explanations, rather than just the input and output variables as is standard
practice. The proposed influence-driven explanations (IDXs) for BCs are
systematically generated using the causal relationships between variables
within the BC, called influences, which are then categorised by logical
requirements, called relation properties, according to their behaviour. These
relation properties both provide guarantees beyond heuristic explanation
methods and allow the information underpinning an explanation to be tailored to
a particular context's and user's requirements, e.g., IDXs may be dialectical
or counterfactual. We demonstrate IDXs' capability to explain various forms of
BCs, e.g., naive or multi-label, binary or categorical, and also integrate
recent approaches to explanations for BCs from the literature. We evaluate IDXs
with theoretical and empirical analyses, demonstrating their considerable
advantages when compared with existing explanation methods.
address the lack of explainability of many of its models. We focus on
explanations for discrete Bayesian network classifiers (BCs), targeting greater
transparency of their inner workings by including intermediate variables in
explanations, rather than just the input and output variables as is standard
practice. The proposed influence-driven explanations (IDXs) for BCs are
systematically generated using the causal relationships between variables
within the BC, called influences, which are then categorised by logical
requirements, called relation properties, according to their behaviour. These
relation properties both provide guarantees beyond heuristic explanation
methods and allow the information underpinning an explanation to be tailored to
a particular context's and user's requirements, e.g., IDXs may be dialectical
or counterfactual. We demonstrate IDXs' capability to explain various forms of
BCs, e.g., naive or multi-label, binary or categorical, and also integrate
recent approaches to explanations for BCs from the literature. We evaluate IDXs
with theoretical and empirical analyses, demonstrating their considerable
advantages when compared with existing explanation methods.
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/2012.05773v2
Grant Number
RCSRF2021\11\45
Subjects
cs.AI
cs.AI
Notes
11 pages, 2 figures
Publication Status
Published