用于分类的不确定性感知集成深度随机神经网络
Uncertainty-Aware Ensemble Deep Randomized Neural Networks for Classification
浏览论文内容
中文总结 AI 辅助
针对现有深度随机神经网络对噪声/异常值鲁棒性不足的问题，提出IF-dRVFL与IF-edRVFL框架，通过直觉模糊理论分配样本自适应权重，在UCI、KEEL数据集上的实验验证了其性能优于现有SOTA方法。
中文摘要 AI 辅助
当前最先进的（SOTA）深度随机神经网络，如深度随机向量函数链接网络（deep Random Vector Functional Link，dRVFL）和集成深度RVFL（ensemble deep RVFL，edRVFL），对所有训练样本一视同仁，这限制了它们在应用于包含噪声和异常值的真实世界数据集时的鲁棒性和有效性。此外，受污染特征在隐藏层中的传播会对这些模型的决策能力产生负面影响。为克服这些局限，我们提出直觉模糊dRVFL（intuitionistic fuzzy dRVFL，IF-dRVFL）和直觉模糊edRVFL（intuitionistic fuzzy edRVFL，IF-edRVFL）框架以增强模型鲁棒性。所提模型结合直觉模糊理论，通过联合考虑每个样本的隶属度和非隶属度，在核空间中利用样本邻域信息；隶属度基于样本到其对应类中心的距离计算，非隶属度则量化局部邻域内的样本异质性。这些度量被用于为训练样本分配自适应权重，从而实现对干净、噪声和异常值数据点的有效区分。在含与不含高斯噪声的UCI和KEEL基准数据集上开展的大量实验表明，所提IF-dRVFL和IF-edRVFL模型优于现有SOTA模糊及非模糊方法。源代码可在该https URL获取。
英文摘要
The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training samples uniformly, which limits their robustness and effectiveness when applied to real-world datasets containing noise and outliers. Furthermore, the propagation of contaminated features across hidden layers negatively influences the decision-making capability of these models. To overcome these limitations, we propose intuitionistic fuzzy dRVFL (IF-dRVFL) and intuitionistic fuzzy edRVFL (IF-edRVFL) frameworks that enhance model robustness. The proposed models unify intuitionistic fuzzy theory to exploit sample neighborhood information in the kernel space by jointly considering membership and non-membership degrees for each sample. Membership degrees are computed based on the distance of samples from their respective class centroids, while non-membership degrees quantify sample heterogeneity within local neighborhoods. These measures are employed to assign adaptive weights to training samples, enabling effective discrimination among clean, noisy, and outlier data points. Extensive experiments conducted on UCI and KEEL benchmark datasets, with and without the presence of Gaussian noise, demonstrate the superiority of the proposed IF-dRVFL and IF-edRVFL models over existing SOTA fuzzy and non-fuzzy approaches. The source code is available at https://github.com/mtanveer1/IF-edRVFL.
发表机构
- Indian Institute of Technology Indore（印度印多尔印度理工学院）
- Qatar University（卡塔尔大学）
机构由 AI 辅助整理，请以论文原文为准。
