论文标题
非线性维度降低的深层歧管变换
Deep Manifold Transformation for Nonlinear Dimensionality Reduction
论文作者
论文摘要
基于多种学习的编码器一直在非线性维度降低（NLDR）中发挥重要作用，以进行数据探索。但是，现有方法通常无法保留数据的几何，拓扑和/或分布结构。在本文中，我们提出了一个深层的多种学习框架，称为无监督的NLDR和嵌入学习的深层多种转化（DMT）。 DMT通过使用跨层局部保留（LGP）约束来增强深层神经网络。 LGP的约束构成了深层流动学习的损失，并充当NLDR网络培训的几何正规化器。关于合成和现实世界数据的广泛实验表明，在保留数据结构方面，DMT网络的表现优于现有基于领先的NLDR方法。
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 distributional structures of data. In this paper, we propose a deep manifold learning framework, called deep manifold transformation (DMT) for unsupervised NLDR and embedding learning. DMT enhances deep neural networks by using cross-layer local geometry-preserving (LGP) constraints. The LGP constraints constitute the loss for deep manifold learning and serve as geometric regularizers for NLDR network training. Extensive experiments on synthetic and real-world data demonstrate that DMT networks outperform existing leading manifold-based NLDR methods in terms of preserving the structures of data.
