Studying Trustworthiness of Neural-Symbolic Models for Enterprise Model Classification via Post-Hoc Explanation

Alexander Smirnov, Anton Agafonov, Nikolay Shilov

2024

Abstract

Neural network-based enterprise modelling support is becoming popular. However, in practical enterprise modelling scenarios, the quantity of accessible data proves inadequate for efficient training of deep neural networks. A strategy to solve this problem can involve integrating symbolic knowledge to neural networks. In previous publications, it was shown that this strategy is useful, but the trust issue was not considered. The paper is aimed to analyse if the trained neural-symbolic models just “learn” the samples better or rely on the meaningful indicators for enterprise model classification. The post-hoc explanation (specifically, the concept extraction) has been used as the studying technique. The experimental results showed that embedding symbolic knowledge does not only improve the learning capabilities but also increases the trustworthiness of the trained machine learning models for enterprise model classification.

Paper Citation

in Harvard Style

Smirnov A., Agafonov A. and Shilov N. (2024). Studying Trustworthiness of Neural-Symbolic Models for Enterprise Model Classification via Post-Hoc Explanation. In Proceedings of the 26th International Conference on Enterprise Information Systems - Volume 1: ICEIS; ISBN 978-989-758-692-7, SciTePress, pages 873-880. DOI: 10.5220/0012730700003690

in Bibtex Style

@conference{iceis24,
author={Alexander Smirnov and Anton Agafonov and Nikolay Shilov},
title={Studying Trustworthiness of Neural-Symbolic Models for Enterprise Model Classification via Post-Hoc Explanation},
booktitle={Proceedings of the 26th International Conference on Enterprise Information Systems - Volume 1: ICEIS},
year={2024},
pages={873-880},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012730700003690},
isbn={978-989-758-692-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 26th International Conference on Enterprise Information Systems - Volume 1: ICEIS
TI - Studying Trustworthiness of Neural-Symbolic Models for Enterprise Model Classification via Post-Hoc Explanation
SN - 978-989-758-692-7
AU - Smirnov A.
AU - Agafonov A.
AU - Shilov N.
PY - 2024
SP - 873
EP - 880
DO - 10.5220/0012730700003690
PB - SciTePress