A Class Inference Scheme With Dempster-Shafer Theory for Learning Fuzzy-Classifier Systems

2025-02-14

ACM Transactions on Evolutionary Learning and Optimization

AI Summary

Existing learning fuzzy classification systems (LFCSs) commonly employ voting- or winner-takes-all–based class inference mechanisms, which suffer from strong dependence on training data, poor generalization, and an inability to model epistemic uncertainty. To address these limitations, this paper introduces Dempster–Shafer (DS) evidence theory into LFCS class inference for the first time, proposing a novel evidential fusion reasoning framework. It aggregates evidence from multiple fuzzy rules via belief mass assignment and explicitly incorporates an “I don’t know” state to represent cognitive uncertainty. Implemented within the Fuzzy-UCS architecture, the method is rigorously evaluated on 30 real-world datasets. Results demonstrate statistically significant improvements in test macro-F1 scores, smoother decision boundaries, interpretable confidence estimates, and enhanced model robustness and deployment reliability.

Technology Category

• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

The decision-making process significantly influences the predictions of machine learning models. This is especially important in rule-based systems such as Learning Fuzzy-Classifier Systems (LFCSs) where the selection and application of rules directly determine prediction accuracy and reliability. LFCSs combine evolutionary algorithms with supervised learning to optimize fuzzy classification rules, offering enhanced interpretability and robustness. Despite these advantages, research on improving decision-making mechanisms (i.e., class inference schemes) in LFCSs remains limited. Most LFCSs use voting-based or single-winner-based inference schemes. These schemes rely on classification performance on training data and may not perform well on unseen data, risking overfitting. To address these limitations, this article introduces a novel class inference scheme for LFCSs based on the Dempster-Shafer Theory of Evidence (DS theory). The proposed scheme handles uncertainty well. By using the DS theory, the scheme calculates belief masses (i.e., measures of belief) for each specific class and the “I don’t know” state from each fuzzy rule and infers a class from these belief masses. Unlike the conventional schemes, the proposed scheme also considers the “I don’t know” state that reflects uncertainty, thereby improving the transparency and reliability of LFCSs. Applied to a variant of LFCS (i.e., Fuzzy-UCS), the proposed scheme demonstrates statistically significant improvements in terms of test macro F1 scores across 30 real-world datasets compared to conventional voting-based and single-winner-based fuzzy inference schemes. It forms smoother decision boundaries, provides reliable confidence measures, and enhances the robustness and generalizability of LFCSs in real-world applications.

Problem

• Improving decision-making in Learning Fuzzy-Classifier Systems (LFCSs)
• Addressing overfitting in voting-based inference schemes
• Enhancing LFCS reliability using Dempster-Shafer Theory

Innovation

• Uses Dempster-Shafer Theory for uncertainty handling
• Incorporates 'I don't know' state for reliability
• Improves F1 scores and decision boundaries