A dimensionality reduction technique based on the Gromov-Wasserstein distance
This is an incremental improvement for data scientists working with complex high-dimensional datasets, offering a new probabilistic view of existing algorithms like MDS and Isomap.
The paper tackles the problem of dimensionality reduction for analyzing relationships between objects in data science by proposing a new method based on the Gromov-Wasserstein distance and optimal transportation theory, which embeds high-dimensional data into a lower-dimensional space through gradient descent to provide a robust and efficient solution.
Analyzing relationships between objects is a pivotal problem within data science. In this context, Dimensionality reduction (DR) techniques are employed to generate smaller and more manageable data representations. This paper proposes a new method for dimensionality reduction, based on optimal transportation theory and the Gromov-Wasserstein distance. We offer a new probabilistic view of the classical Multidimensional Scaling (MDS) algorithm and the nonlinear dimensionality reduction algorithm, Isomap (Isometric Mapping or Isometric Feature Mapping) that extends the classical MDS, in which we use the Gromov-Wasserstein distance between the probability measure of high-dimensional data, and its low-dimensional representation. Through gradient descent, our method embeds high-dimensional data into a lower-dimensional space, providing a robust and efficient solution for analyzing complex high-dimensional datasets.