提出新方法让模糊系统在保持高准确率的同时提升可解释性。
Alternating Bi-Objective Optimization for Explainable Neuro-Fuzzy Systems
- 交替梯度优化，分离可解释性与性能目标
- 在9个数据集上实现高区分度且精度不降
- 能发现传统方法无法触及的最优解区域
模糊系统因其基于规则的结构和语言变量，在可解释人工智能中具有巨大潜力。现有方法要么通过计算成本高的进化多目标优化（MOO）处理准确率-可解释性权衡，要么采用梯度基标量法，无法恢复非凸帕累托区域。本文提出X-ANFIS，一种用于可解释自适应神经模糊推理系统的交替双目标梯度优化方案。采用柯西型隶属函数，在语义可控初始化下实现稳定训练，并通过交替梯度传递将可解释性目标与性能目标解耦。在九个UCI回归数据集上约5000次实验验证表明，X-ANFIS始终达到目标区分度，同时保持有竞争力的预测准确率，成功恢复了超出MOO帕累托前沿凸包的解。
原文摘要 · Abstract (English)
Fuzzy systems show strong potential in explainable AI due to their rule-based architecture and linguistic variables. Existing approaches navigate the accuracy-explainability trade-off either through evolutionary multi-objective optimization (MOO), which is computationally expensive, or gradient-based scalarization, which cannot recover non-convex Pareto regions. We propose X-ANFIS, an alternating bi-objective gradient-based optimization scheme for explainable adaptive neuro-fuzzy inference systems. Cauchy membership functions are used for stable training under semantically controlled initializations, and a differentiable explainability objective is introduced and decoupled from the performance objective through alternating gradient passes. Validated in approximately 5,000 experiments on nine UCI regression datasets, X-ANFIS consistently achieves target distinguishability while maintaining competitive predictive accuracy, recovering solutions beyond the convex hull of the MOO Pareto front.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。