DeepAI AI Chat
Log In Sign Up

Overlaying Spaces and Practical Applicability of Complex Geometries

07/05/2020
by   Kirill Shevkunov, et al.
Moscow Institute of Physics and Technology
0

Recently, non-Euclidean spaces became popular for embedding structured data. Following hyperbolic and spherical spaces, more general product spaces have been proposed. However, searching for the best configuration of a product space is a resource-intensive procedure, which reduces the practical applicability of the idea. We introduce a novel concept of overlaying spaces that does not have the problem of configuration search and outperforms the competitors in structured data embedding tasks, when the aim is to preserve all distances. On the other hand, for local loss functions (e.g., for ranking losses), the dot-product similarity, which is often overlooked in graph embedding literature since it cannot be converted to a metric, outperforms all metric spaces. We discuss advantages of the dot product over proper metric spaces.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/17/2021

Switch Spaces: Learning Product Spaces with Sparse Gating

Learning embedding spaces of suitable geometry is critical for represent...
02/19/2021

Linear Classifiers in Mixed Constant Curvature Spaces

Embedding methods for mixed-curvature spaces are powerful techniques for...
08/10/2022

Neural Embedding: Learning the Embedding of the Manifold of Physics Data

In this paper, we present a method of embedding physics data manifolds w...
10/08/2019

Beyond Vector Spaces: Compact Data Representationas Differentiable Weighted Graphs

Learning useful representations is a key ingredient to the success of mo...
10/08/2019

Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs

Learning useful representations is a key ingredient to the success of mo...
04/08/2021

Advances in Metric Ramsey Theory and its Applications

Metric Ramsey theory is concerned with finding large well-structured sub...
09/19/2022

Dual-Geometric Space Embedding Model for Two-View Knowledge Graphs

Two-view knowledge graphs (KGs) jointly represent two components: an ont...