Loading...
On the interpretability of fuzzy cognitive maps
Nápoles,Gonzalo Ranković,Nevena Salgueiro,Yamisleydi
Nápoles,Gonzalo
Ranković,Nevena
Salgueiro,Yamisleydi
Abstract
This paper proposes a post-hoc explanation method for computing concept attribution in Fuzzy Cognitive Map (FCM) models used for scenario analysis, based on SHapley Additive exPlanations (SHAP) values. The proposal is inspired by the lack of approaches to exploit the often-claimed intrinsic interpretability of FCM models while considering their dynamic properties. Our method uses the initial activation values of concepts as input features, while the outputs are considered as the hidden states produced by the FCM model during the recurrent reasoning process. Hence, the relevance of neural concepts is computed taking into account the model’s dynamic properties and hidden states, which result from the interaction among the initial conditions, the weight matrix, the activation function, and the selected reasoning rule. The proposed post-hoc method can handle situations where the FCM model might not converge or converge to a unique fixed-point attractor where the final activation values of neural concepts are invariant. The effectiveness of the proposed approach is demonstrated through experiments conducted on real-world case studies.
Description
Publisher Copyright: © 2023 The Author(s)
Date
2023-12-03
Journal Title
Journal ISSN
Volume Title
Publisher
Files
Research Projects
Organizational Units
Journal Issue
Keywords
Concept relevance, Decision making, Fuzzy Cognitive Maps, Interpretability
Citation
Nápoles, G, Ranković, N & Salgueiro, Y 2023, 'On the interpretability of fuzzy cognitive maps', Knowledge-Based Systems, vol. 281, no. 111078, 111078. https://doi.org/10.1016/j.knosys.2023.111078