Deep Manifold Transformation for Nonlinear Dimensionality Reduction
arXiv:2010.14831
Abstract
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.
References in corpus (6)
- A Simple Framework for Contrastive Learning of Visual Representations
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Spectrally-normalized margin bounds for neural networks
- Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
- Lipschitz Generative Adversarial Nets
- Markov-Lipschitz Deep Learning