论文标题
可解释的维度通过特征保留歧管近似和投影降低
Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection
论文作者
论文摘要
由于在低维嵌入空间中没有源特征，因此非线性维度降低缺乏可解释性。我们提出了一个可解释的方法效果图，以通过切线空间嵌入来保留源功能。我们建议的核心是利用局部奇异值分解（SVD）来近似通过保持对齐方式嵌入到低维空间的切线空间。基于嵌入切线空间，功能映射可以通过本地展示源特征和特征重要性来实现可解释性。此外，功能图将各向异性投影嵌入数据点，以保留局部相似性和原始密度。我们将功能示范应用于解释数字分类，对象检测和MNIST对抗性示例。 FARTMAP使用源功能明确区分数字和对象，并解释对抗性示例的错误分类。我们还将功能图与本地和全球指标的其他最先进的方法进行了比较。
Nonlinear dimensionality reduction lacks interpretability due to the absence of source features in low-dimensional embedding space. We propose an interpretable method featMAP to preserve source features by tangent space embedding. The core of our proposal is to utilize local singular value decomposition (SVD) to approximate the tangent space which is embedded to low-dimensional space by maintaining the alignment. Based on the embedding tangent space, featMAP enables the interpretability by locally demonstrating the source features and feature importance. Furthermore, featMAP embeds the data points by anisotropic projection to preserve the local similarity and original density. We apply featMAP to interpreting digit classification, object detection and MNIST adversarial examples. FeatMAP uses source features to explicitly distinguish the digits and objects and to explain the misclassification of adversarial examples. We also compare featMAP with other state-of-the-art methods on local and global metrics.
