无需重训练即可快速调整预测区间，提升深度学习不确定性量化效率
Adapting GT2-FLS for Uncertainty Quantification: A Blueprint Calibration Strategy
- 基于α-平面关系设计校准策略，实现无重训练的覆盖率动态调整
- 在高维数据上验证，校准后模型保持高精度且计算开销大幅降低
- 适合需实时不确定性估计的医疗、自动驾驶等关键场景
不确定性量化（UQ）对高风险场景中部署可靠深度学习模型至关重要。近年来，广义型2模糊逻辑系统（GT2-FLS）被证明能有效进行UQ，通过预测区间（PIs）捕捉不确定性。然而，现有方法常面临计算效率低和适应性差的问题，生成新覆盖水平（ϕ_d）的PIs通常需重新训练模型。直接估计完整条件分布的方法也计算成本高昂，限制了实际应用。本文提出一种针对GT2-FLS的蓝图校准策略，可在不重训练的前提下高效适配任意ϕ_d。通过分析α-平面类型简化集与不确定性覆盖的关系，开发了基于查表和无导数优化两种校准方法，使GT2-FLS在显著降低计算开销的同时，仍能生成准确可靠的预测区间。在高维数据集上的实验表明，校准后的模型在不确定性量化方面表现优异，展现出可扩展且实用的应用潜力。
原文摘要 · Abstract (English)
Uncertainty Quantification (UQ) is crucial for deploying reliable Deep Learning (DL) models in high-stakes applications. Recently, General Type-2 Fuzzy Logic Systems (GT2-FLSs) have been proven to be effective for UQ, offering Prediction Intervals (PIs) to capture uncertainty. However, existing methods often struggle with computational efficiency and adaptability, as generating PIs for new coverage levels $(ϕ_d)$ typically requires retraining the model. Moreover, methods that directly estimate the entire conditional distribution for UQ are computationally expensive, limiting their scalability in real-world scenarios. This study addresses these challenges by proposing a blueprint calibration strategy for GT2-FLSs, enabling efficient adaptation to any desired $ϕ_d$ without retraining. By exploring the relationship between $α$-plane type reduced sets and uncertainty coverage, we develop two calibration methods: a lookup table-based approach and a derivative-free optimization algorithm. These methods allow GT2-FLSs to produce accurate and reliable PIs while significantly reducing computational overhead. Experimental results on high-dimensional datasets demonstrate that the calibrated GT2-FLS achieves superior performance in UQ, highlighting its potential for scalable and practical applications.
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。