Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks

Annet Onnes; Silja Renooij

doi:10.1007/978-3-032-05134-9_4

Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks

Annet Onnes^*
, Silja Renooij

^*Corresponding author for this work

Sub Intelligent Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

This paper proposes a quantification method to support the elicitation process for Bayesian network construction. The method aims at reducing the number of subjective modelling choices that need to be made to arrive at an initial quantification of a Bayesian network. Our method allows domain experts to express their knowledge in the form of probability constraints. Then, exploiting recent insights concerning the computation of entropy in Bayesian networks, it uses the Maximum Entropy principle to determine a single quantification that makes no assumptions beyond the information provided by the domain experts. The quantification can be used in an iterative probability elicitation process. We provide an overview of our maximum entropy-based quantification method, detail how to express experts’ constraints for this technique for entropy maximisation and illustrate the method using an example.

Original language	English
Title of host publication	Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 18th European Conference, ECSQARU 2025, Proceedings
Editors	Kai Sauerwald, Matthias Thimm
Publisher	Springer
Pages	46-60
Number of pages	15
ISBN (Electronic)	978-3-032-05134-9
ISBN (Print)	978-3-032-05133-2
DOIs	https://doi.org/10.1007/978-3-032-05134-9_4
Publication status	Published - 24 Sept 2025
Event	18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2025 - Hagen, Germany Duration: 23 Sept 2025 → 26 Sept 2025

Publication series

Name	Lecture Notes in Computer Science
Volume	16099 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2025
Country/Territory	Germany
City	Hagen
Period	23/09/25 → 26/09/25

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Keywords

Bayesian Networks
Idioms
Maximum Entropy
Qualitative Constraints

Access to Document

10.1007/978-3-032-05134-9_4

Cite this

Onnes, A., & Renooij, S. (2025). Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks. In K. Sauerwald, & M. Thimm (Eds.), Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 18th European Conference, ECSQARU 2025, Proceedings (pp. 46-60). (Lecture Notes in Computer Science; Vol. 16099 LNCS). Springer. https://doi.org/10.1007/978-3-032-05134-9_4

@inproceedings{bfe413f38ee64ec598e4dbeb30337a42,

title = "Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks",

abstract = "This paper proposes a quantification method to support the elicitation process for Bayesian network construction. The method aims at reducing the number of subjective modelling choices that need to be made to arrive at an initial quantification of a Bayesian network. Our method allows domain experts to express their knowledge in the form of probability constraints. Then, exploiting recent insights concerning the computation of entropy in Bayesian networks, it uses the Maximum Entropy principle to determine a single quantification that makes no assumptions beyond the information provided by the domain experts. The quantification can be used in an iterative probability elicitation process. We provide an overview of our maximum entropy-based quantification method, detail how to express experts{\textquoteright} constraints for this technique for entropy maximisation and illustrate the method using an example.",

keywords = "Bayesian Networks, Idioms, Maximum Entropy, Qualitative Constraints",

author = "Annet Onnes and Silja Renooij",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2025 ; Conference date: 23-09-2025 Through 26-09-2025",

year = "2025",

month = sep,

day = "24",

doi = "10.1007/978-3-032-05134-9\_4",

language = "English",

isbn = "978-3-032-05133-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "46--60",

editor = "Kai Sauerwald and Matthias Thimm",

booktitle = "Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 18th European Conference, ECSQARU 2025, Proceedings",

}

Onnes, A & Renooij, S 2025, Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks. in K Sauerwald & M Thimm (eds), Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 18th European Conference, ECSQARU 2025, Proceedings. Lecture Notes in Computer Science, vol. 16099 LNCS, Springer, pp. 46-60, 18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2025, Hagen, Germany, 23/09/25. https://doi.org/10.1007/978-3-032-05134-9_4

Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks. / Onnes, Annet; Renooij, Silja.
Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 18th European Conference, ECSQARU 2025, Proceedings. ed. / Kai Sauerwald; Matthias Thimm. Springer, 2025. p. 46-60 (Lecture Notes in Computer Science; Vol. 16099 LNCS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks

AU - Onnes, Annet

AU - Renooij, Silja

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2025/9/24

Y1 - 2025/9/24

N2 - This paper proposes a quantification method to support the elicitation process for Bayesian network construction. The method aims at reducing the number of subjective modelling choices that need to be made to arrive at an initial quantification of a Bayesian network. Our method allows domain experts to express their knowledge in the form of probability constraints. Then, exploiting recent insights concerning the computation of entropy in Bayesian networks, it uses the Maximum Entropy principle to determine a single quantification that makes no assumptions beyond the information provided by the domain experts. The quantification can be used in an iterative probability elicitation process. We provide an overview of our maximum entropy-based quantification method, detail how to express experts’ constraints for this technique for entropy maximisation and illustrate the method using an example.

AB - This paper proposes a quantification method to support the elicitation process for Bayesian network construction. The method aims at reducing the number of subjective modelling choices that need to be made to arrive at an initial quantification of a Bayesian network. Our method allows domain experts to express their knowledge in the form of probability constraints. Then, exploiting recent insights concerning the computation of entropy in Bayesian networks, it uses the Maximum Entropy principle to determine a single quantification that makes no assumptions beyond the information provided by the domain experts. The quantification can be used in an iterative probability elicitation process. We provide an overview of our maximum entropy-based quantification method, detail how to express experts’ constraints for this technique for entropy maximisation and illustrate the method using an example.

KW - Bayesian Networks

KW - Idioms

KW - Maximum Entropy

KW - Qualitative Constraints

UR - https://www.scopus.com/pages/publications/105018304650

U2 - 10.1007/978-3-032-05134-9_4

DO - 10.1007/978-3-032-05134-9_4

M3 - Conference contribution

AN - SCOPUS:105018304650

SN - 978-3-032-05133-2

T3 - Lecture Notes in Computer Science

SP - 46

EP - 60

BT - Symbolic and Quantitative Approaches to Reasoning with Uncertainty - 18th European Conference, ECSQARU 2025, Proceedings

A2 - Sauerwald, Kai

A2 - Thimm, Matthias

PB - Springer

T2 - 18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2025

Y2 - 23 September 2025 through 26 September 2025

ER -