A review of explanation methods for Bayesian networks

Lacave, Carmen; Díez, F. J.

doi:10.1017/s026988890200019x

Cited by 177 publications

(135 citation statements)

References 35 publications

Supporting

Mentioning

134

Contrasting

Unclassified

Order By: Relevance

“…An overview of research on explaining Bayesian networks can be found in Lacave and Díez (2002). Typically, the explanation of Bayesian networks attempts to explain why certain modelling choices were made and why the network produces a certain result given these choices.…”

Section: Discussionmentioning

confidence: 99%

A method for explaining Bayesian networks for legal evidence with scenarios

et al. 2016

View full text Add to dashboard Cite

In a criminal trial, a judge or jury needs to reason about what happened based on the available evidence, often including statistical evidence. While a probabilistic approach is suitable for analysing the statistical evidence, a judge or jury may be more inclined to use a narrative or argumentative approach when considering the case as a whole. In this paper we propose a combination of two approaches, combining Bayesian networks with scenarios. Whereas a Bayesian network is a popular tool for analysing parts of a case, constructing and understanding a network for an entire case is not straightforward. We propose an explanation method for understanding a Bayesian network in terms of scenarios. This method builds on a previously proposed construction method, which we slightly adapt with the use of scenario schemes for the purpose of explaining. The resulting structure is explained in terms of scenarios, scenario quality and evidential support. A probabilistic interpretation of scenario quality is provided using the concept of scenario schemes. Finally, the method is evaluated by means of a case study.

show abstract

Section: Discussionmentioning

confidence: 99%

A method for explaining Bayesian networks for legal evidence with scenarios

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Many explanation methods for BNs (see e.g. [4,3]) focus on textual or visual systems. Other work on argument extraction includes that of Keppens [2], who focuses on Argument Diagrams.…”

Section: Discussionmentioning

confidence: 99%

Explaining Bayesian Networks Using Argumentation

Timmer

Meyer

Prakken

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Qualitative and quantitative systems to deal with uncertainty coexist. Bayesian networks are a well known tool in probabilistic reasoning. For non-statistical experts, however, Bayesian networks may be hard to interpret. Especially since the inner workings of Bayesian networks are complicated they may appear as black box models. Argumentation approaches, on the contrary, emphasise the derivation of results. Argumentation models, however, have notorious difficulty dealing with probabilities. In this paper we formalise a two-phase method to extract probabilistically supported arguments from a Bayesian network. First, from a BN we construct a support graph, and, second, given a set of observations we build arguments from that support graph. Such arguments can facilitate the correct interpretation and explanation of the evidence modelled in the Bayesian network.

show abstract

“…Tullio et al reported that, given some basic types of explanations, end users can understand how machine learning systems operate [Tullio et al 2007], with the caveat that overcoming any preliminary faulty assumptions may be problematic. More sophisticated, though computationally expensive, explanation algorithms have been developed for general Bayesian networks [Lacave and Diez 2002]. Finally, Lim et al ] investigated the usefulness of the Whyline approach for explaining simple decision trees and found that the approach was viable for explaining this relatively understandable form of machine learning.…”

Section: Communicating With Machine Learning Systems **D275mentioning

confidence: 99%

“…As an example, Bayesian networks provide a sophisticated mechanism for providing detailed explanations of how different pieces of evidence influence the final prediction made by the algorithm [Lacave and Diez 2002], but this is computationally expensive. A current challenge for machine learning is to develop answers to Why questions of statistical machine learning algorithms that can be efficiently computed.…”

Section: Supporting Answers To the Why Questions Beyond Naïve Bayes **D1mentioning

confidence: 99%

Why-oriented end-user debugging of naive Bayes text classification

Kulesza

Stumpf

Wong

et al. 2011

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

This is the accepted version of the paper.This version of the publication may differ from the final published version. **Vocab: "data" is plural. So, need "data are" instead of "data is". **Vocab: It's a Why-oriented approach (capitalized) **Vocab: It's naïve Bayes (lower-case 'n') **Vocab/numbering: change the following globally: Permanent repository linkPrinciple (iv) -> Principle ML-2 **Length: TiiS suggests manuscripts be between 10,000 and 15,000 words. Machine learning techniques are increasingly used in intelligent assistants, software targeted at and continuously adapting to assisting end users with email, shopping, and other tasks. Examples include desktop SPAM filters, recommender systems, and handwriting recognition. Fixing such intelligent assistants when they learn incorrect behavior, however, has received only limited attention. To directly support end-user "debugging" of assistant behaviors learned via statistical machine learning, we present a Why-oriented approach that allows users to ask questions about how the assistant made its predictions, provides answers to these "why" questions, and allows users to interactively change these answers to "debug" these assistants' current and future predictions. To understand the strengths and weaknesses of the approach, we conducted an exploratory study to investigate barriers that participants would encounter when debugging an intelligent assistant using our approach, and the information those participants requested to overcome these barriers. To help ensure the inclusiveness of our investigation, we also explored how gender differences played a role in barriers and information needs. We then use these results to consider opportunities for Why-oriented approaches to address the users' barriers and information needs.

show abstract

A review of explanation methods for Bayesian networks

Cited by 177 publications

References 35 publications

A method for explaining Bayesian networks for legal evidence with scenarios

A method for explaining Bayesian networks for legal evidence with scenarios

Explaining Bayesian Networks Using Argumentation

Why-oriented end-user debugging of naive Bayes text classification

Contact Info

Product

Resources

About