Home > Research > Publications & Outputs > Harnessing Prior Knowledge for Explainable Mach...

Research

Links

Text available via DOI:

View graph of relations

Harnessing Prior Knowledge for Explainable Machine Learning: An Overview

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Harnessing Prior Knowledge for Explainable Machine Learning: An Overview. / Beckh, Katharina; Müller, Sebastian; Jakobs, Matthias et al.
2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE, 2023. p. 450-463.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Beckh, K, Müller, S, Jakobs, M, Toborek, V, Tan, H, Fischer, R, Welke, P, Houben, S & von Rüden, L 2023, Harnessing Prior Knowledge for Explainable Machine Learning: An Overview. in 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE, pp. 450-463. https://doi.org/10.1109/SATML54575.2023.00038

APA

Beckh, K., Müller, S., Jakobs, M., Toborek, V., Tan, H., Fischer, R., Welke, P., Houben, S., & von Rüden, L. (2023). Harnessing Prior Knowledge for Explainable Machine Learning: An Overview. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) (pp. 450-463). IEEE. https://doi.org/10.1109/SATML54575.2023.00038

Vancouver

Beckh K, Müller S, Jakobs M, Toborek V, Tan H, Fischer R et al. Harnessing Prior Knowledge for Explainable Machine Learning: An Overview. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE. 2023. p. 450-463 Epub 2023 Feb 8. doi: 10.1109/SATML54575.2023.00038

Author

Beckh, Katharina ; Müller, Sebastian ; Jakobs, Matthias et al. / Harnessing Prior Knowledge for Explainable Machine Learning : An Overview. 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE, 2023. pp. 450-463

Bibtex

@inproceedings{34d7c780386040968bd8917e5288a58a,
title = "Harnessing Prior Knowledge for Explainable Machine Learning: An Overview",
abstract = "The application of complex machine learning models has elicited research to make them more explainable. However, most explainability methods cannot provide insight beyond the given data, requiring additional information about the context. We argue that harnessing prior knowledge improves the accessibility of explanations. We hereby present an overview of integrating prior knowledge into machine learning systems in order to improve explainability. We introduce a categorization of current research into three main categories which integrate knowledge either into the machine learning pipeline, into the explainability method or derive knowledge from explanations. To classify the papers, we build upon the existing taxonomy of informed machine learning and extend it from the perspective of explainability. We conclude with open challenges and research directions.",
author = "Katharina Beckh and Sebastian M{\"u}ller and Matthias Jakobs and Vanessa Toborek and Hanxiao Tan and Raphael Fischer and Pascal Welke and Sebastian Houben and {von R{\"u}den}, Laura",
note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",
year = "2023",
month = jun,
day = "1",
doi = "10.1109/SATML54575.2023.00038",
language = "English",
isbn = "9781665463003",
pages = "450--463",
booktitle = "2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Harnessing Prior Knowledge for Explainable Machine Learning

T2 - An Overview

AU - Beckh, Katharina

AU - Müller, Sebastian

AU - Jakobs, Matthias

AU - Toborek, Vanessa

AU - Tan, Hanxiao

AU - Fischer, Raphael

AU - Welke, Pascal

AU - Houben, Sebastian

AU - von Rüden, Laura

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2023/6/1

Y1 - 2023/6/1

N2 - The application of complex machine learning models has elicited research to make them more explainable. However, most explainability methods cannot provide insight beyond the given data, requiring additional information about the context. We argue that harnessing prior knowledge improves the accessibility of explanations. We hereby present an overview of integrating prior knowledge into machine learning systems in order to improve explainability. We introduce a categorization of current research into three main categories which integrate knowledge either into the machine learning pipeline, into the explainability method or derive knowledge from explanations. To classify the papers, we build upon the existing taxonomy of informed machine learning and extend it from the perspective of explainability. We conclude with open challenges and research directions.

AB - The application of complex machine learning models has elicited research to make them more explainable. However, most explainability methods cannot provide insight beyond the given data, requiring additional information about the context. We argue that harnessing prior knowledge improves the accessibility of explanations. We hereby present an overview of integrating prior knowledge into machine learning systems in order to improve explainability. We introduce a categorization of current research into three main categories which integrate knowledge either into the machine learning pipeline, into the explainability method or derive knowledge from explanations. To classify the papers, we build upon the existing taxonomy of informed machine learning and extend it from the perspective of explainability. We conclude with open challenges and research directions.

U2 - 10.1109/SATML54575.2023.00038

DO - 10.1109/SATML54575.2023.00038

M3 - Conference contribution/Paper

SN - 9781665463003

SP - 450

EP - 463

BT - 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

PB - IEEE

ER -