Uniform Manifold Approximation with Two-phase Optimization

@article{Jeon2022UniformMA,
  title={Uniform Manifold Approximation with Two-phase Optimization},
  author={Hyeon Jeon and Hyung-Kwon Ko and Soo Bong Lee and Jaemin Jo and Jinwook Seo},
  journal={ArXiv},
  year={2022},
  volume={abs/2205.00420}
}
We introduce Uniform Manifold Approximation with Two-phase Optimization (UMATO), a dimensionality reduction (DR) technique that improves UMAP to capture the global structure of high- dimensional data more accurately. In UMATO, optimization is divided into two phases so that the resulting embeddings can depict the global structure reliably while preserving the local structure with sufficient accuracy. As the first phase, hub points are identified and projected to construct a skeletal layout for the… 

Figures and Tables from this paper

Transcriptomic Mapping of Neural Diversity, Differentiation and Functional Trajectory in iPSC-Derived 3D Brain Organoid Models
TLDR
The results caution against use of organoids to model pathophysiology and drug response at this advanced time point and provide insights to tune in vitro iPSC differentiation protocols to achieve desired neuronal functionality and improve current protocols.

References

SHOWING 1-10 OF 41 REFERENCES
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
TLDR
The UMAP algorithm is competitive with t-SNE for visualization quality, and arguably preserves more of the global structure with superior run time performance.
Two key properties of dimensionality reduction methods
  • J. LeeM. Verleysen
  • Computer Science
    2014 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)
  • 2014
TLDR
This paper identifies two important properties that enable some recent methods like stochastic neighborhood embedding and its variants to produce improved visualizations of high-dimensional data, and shows that equipping classical methods with the missing properties significantly improves their results.
HUMAP: Hierarchical Uniform Manifold Approximation and Projection
TLDR
This work presents HUMAP, a novel hierarchical dimensionality reduction technique designed to be flexible on preserving local and global structures and preserve the mental map throughout hierarchical exploration, and provides empirical evidence of the technique’s superiority compared with current hierarchical approaches.
Hierarchical Stochastic Neighbor Embedding
TLDR
This work introduces Hierarchical Stochastic Neighbor Embedding (Hierarchical‐SNE), a hierarchical representation of the data that incorporates the well‐known mantra of Overview‐First, Details‐On‐Demand in non‐linear dimensionality reduction, and explains how it scales to the analysis of big datasets.
Bringing UMAP Closer to the Speed of Light with GPU Acceleration
TLDR
A number of techniques are shown that can be used to make a faster and more faithful GPU version of UMAP, and obtain speedups of up to 100x in practice.
GPGPU Linear Complexity t-SNE Optimization
TLDR
This work presents a novel approach to the minimization of the t-SNE objective function that heavily relies on graphics hardware and has linear computational complexity, and proposes to approximate the repulsive forces between data points by splatting kernel textures for each data point.
Nonlinear Dimensionality Reduction
TLDR
The purpose of the book is to summarize clear facts and ideas about well-known methods as well as recent developments in the topic of nonlinear dimensionality reduction, which encompasses many of the recently developed methods.
Visualizing Large-scale and High-dimensional Data
TLDR
The LargeVis is proposed, a technique that first constructs an accurately approximated K-nearest neighbor graph from the data and then layouts the graph in the low-dimensional space and easily scales to millions of high-dimensional data points.
Topological Autoencoders
TLDR
It is shown that the proposed approach to preserving topological structures of the input space in latent representations of autoencoders exhibits favourable latent representations on a synthetic manifold as well as on real-world image data sets, while preserving low reconstruction errors.
Revisiting Dimensionality Reduction Techniques for Visual Cluster Analysis: An Empirical Study
TLDR
A user study that investigates the influence of different DR techniques on visual cluster analysis and evaluated users' subjective preference of the DR techniques regarding the quality of projected clusters shows that non-linear and Local techniques are preferred in cluster identification and membership identification.
...
...