Feature Learning for Nonlinear Dimensionality Reduction toward Maximal Extraction of Hidden Patterns
This work addresses the challenge of revealing hidden patterns in high-dimensional data for visual analysis, representing an incremental improvement in nonlinear dimensionality reduction methods.
The paper tackles the problem of dimensionality reduction overlooking hidden patterns when manifolds are distorted, by presenting FEALM, a feature learning framework that generates optimized projections to capture important patterns, resulting in significantly different DR outcomes as demonstrated with synthetic and real-world datasets.
Dimensionality reduction (DR) plays a vital role in the visual analysis of high-dimensional data. One main aim of DR is to reveal hidden patterns that lie on intrinsic low-dimensional manifolds. However, DR often overlooks important patterns when the manifolds are distorted or masked by certain influential data attributes. This paper presents a feature learning framework, FEALM, designed to generate a set of optimized data projections for nonlinear DR in order to capture important patterns in the hidden manifolds. These projections produce maximally different nearest-neighbor graphs so that resultant DR outcomes are significantly different. To achieve such a capability, we design an optimization algorithm as well as introduce a new graph dissimilarity measure, named neighbor-shape dissimilarity. Additionally, we develop interactive visualizations to assist comparison of obtained DR results and interpretation of each DR result. We demonstrate FEALM's effectiveness through experiments and case studies using synthetic and real-world datasets.