Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces
This addresses the challenge of principled latent geometry selection for researchers and practitioners using non-Euclidean spaces in machine learning, though it appears incremental as it builds on existing work with product manifolds.
The paper tackles the problem of selecting optimal latent product manifold signatures for machine learning models by introducing a novel distance measure based on the Gromov-Hausdorff distance from metric geometry, and proposes an algorithm to compute this distance and search for the best geometry.
Recent studies propose enhancing machine learning models by aligning the geometric characteristics of the latent space with the underlying data structure. Instead of relying solely on Euclidean space, researchers have suggested using hyperbolic and spherical spaces with constant curvature, or their combinations (known as product manifolds), to improve model performance. However, there exists no principled technique to determine the best latent product manifold signature, which refers to the choice and dimensionality of manifold components. To address this, we introduce a novel notion of distance between candidate latent geometries using the Gromov-Hausdorff distance from metric geometry. We propose using a graph search space that uses the estimated Gromov-Hausdorff distances to search for the optimal latent geometry. In this work we focus on providing a description of an algorithm to compute the Gromov-Hausdorff distance between model spaces and its computational implementation.