NeuroRule: Making Black-Box Neural Networks Explainable through Rule-set Evolution

2026-09-21

AI Summary

本文提出NeuroRule框架，通过规则集进化方法将黑盒神经网络模型转化为可解释的规则集，解决了性能与可解释性之间的权衡问题。

Abstract

High-capacity neural network models have achieved state-of-the-art performance across diverse classification tasks, yet they frequently operate as black-box models, lacking the transparency necessary for critical decision-making. Such opacity creates a persistent trade-off between performance and explainability. This paper proposes a solution to address this gap: the NeuroRule knowledge distillation framework that results in explainable rule-sets from neural network models. NeuroRule adapts the EVOTER rule-set evolution infrastructure to treat neural networks as targets for the evolution process, distilling their performance into concise sets of propositional logic expressions. There are three primary contributions: (1) an evolutionary method for distilling black-box neural network models into explicit rule-set models; (2) a method for making rule sets more explainable by including a conciseness objective to evolution; and (3) a demonstration that the distillation is viable even without access to the original neural network training data. The paper thus establishes that black-box neural network models can be made explainable and therefore useful in real-world applications where trustworthiness is paramount.

Problem

• black-box neural networks
• explainability
• transparency
• classification tasks
• knowledge distillation

Innovation

• NeuroRule
• knowledge distillation
• rule-set evolution
• explainability
• conciseness