Crisp complexity of fuzzy classifiers

2025-04-22

AI Summary

Fuzzy rule-based classifiers suffer from poor interpretability and limited cross-domain acceptance due to conceptual abstraction and opaque decision boundaries in feature space. Method: This paper proposes a systematic reduction framework that equivalently transforms fuzzy rule classifiers into crisp rule classifiers, explicitly exposing their implicit partitioning mechanisms. We innovatively define and quantify “crisp partition complexity”, establishing a reversible mapping and complexity evaluation framework between fuzzy and crisp rule systems. Integrating geometric analysis, rule-space projection, discretization-based simplification, and computational complexity theory, we design multiple algorithms for generating faithful crisp descriptions. Results: Experiments demonstrate that our method accurately characterizes the equivalent crisp complexity of diverse fuzzy classifiers, providing quantifiable theoretical foundations and practical tools for model selection, interpretability–accuracy trade-off analysis, and user-informed decision-making.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Rule-based systems are a very popular form of explainable AI, particularly in the fuzzy community, where fuzzy rules are widely used for control and classification problems. However, fuzzy rule-based classifiers struggle to reach bigger traction outside of fuzzy venues, because users sometimes do not know about fuzzy and because fuzzy partitions are not so easy to interpret in some situations. In this work, we propose a methodology to reduce fuzzy rule-based classifiers to crisp rule-based classifiers. We study different possible crisp descriptions and implement an algorithm to obtain them. Also, we analyze the complexity of the resulting crisp classifiers. We believe that our results can help both fuzzy and non-fuzzy practitioners understand better the way in which fuzzy rule bases partition the feature space and how easily one system can be translated to another and vice versa. Our complexity metric can also help to choose between different fuzzy classifiers based on what the equivalent crisp partitions look like.

Problem

• Convert fuzzy rule-based classifiers to crisp rule-based classifiers
• Analyze complexity of resulting crisp classifiers
• Improve interpretability of fuzzy partitions for non-fuzzy users

Innovation

• Convert fuzzy classifiers to crisp classifiers
• Develop algorithm for crisp rule descriptions
• Analyze complexity of resulting crisp systems