Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Dimensionality ReductionFeature Importanceobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
A Tangent Distance Preserving Dimensionality Reduction Algorithm
This paper considers the problem of nonlinear dimensionality reduction. Unlike existing methods, such as LLE, ISOMAP, which attempt to unfold the true manifold in the low dimensional space, our algorithm tries to preserv…
Dimensionality ReductionFinsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding
Dimensionality reduction is a fundamental task that aims to simplify complex data by reducing its feature dimensionality while preserving essential patterns, with core applications in data analysis and visualisation. To …
Dimensionality ReductionGraph EmbeddingLink PredictionDeep Manifold Transformation for Nonlinear Dimensionality Reduction
Manifold learning-based encoders have been playing important roles in nonlinear dimensionality reduction (NLDR) for data exploration. However, existing methods can often fail to preserve geometric, topological and/or dis…
Dimensionality ReductionA Variational Manifold Embedding Framework for Nonlinear Dimensionality Reduction
Dimensionality reduction algorithms like principal component analysis (PCA) are workhorses of machine learning and neuroscience, but each has well-known limitations. Variants of PCA are simple and interpretable, but not …
Dimensionality ReductionLatent Manifold Reconstruction and Representation with Topological and Geometrical Regularization
Manifold learning aims to discover and represent low-dimensional structures underlying high-dimensional data while preserving critical topological and geometric properties. Existing methods often fail to capture local de…
Dimensionality Reduction