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 strongly distorted or hidden by certain influential data attributes. This paper presents a feature learning framework, FEALM, designed to generate an optimized set of 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, called 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 using synthetic datasets and multiple case studies on real-world datasets.
翻译:在对高维数据进行视觉分析时,多维度减低(DR)在高维数据的视觉分析中发挥着关键作用。DR的一个主要目的是揭示内在低维元体上的隐藏模式。然而,DR往往忽略了当某些有影响的数据属性严重扭曲或隐藏的元体时,DR往往忽略的重要模式。本文介绍了一个特征学习框架FEALM,旨在为非线性DR产生一套优化的数据预测,以捕捉隐藏元体中的重要模式。这些预测产生了极为不同的近邻图,从而使得DR结果大相径庭。为了实现这种能力,我们设计了一种优化算法,并引入了一种新的图异度度测量方法,称为邻居形形形异。此外,我们开发了互动的可视化功能,以协助比较所获得的DR结果和对每项DR结果的解释。我们通过使用合成数据集进行实验和对真实世界数据集进行多重案例研究来证明FEALM的有效性。