What relations are reliably embeddable in Euclidean space?

03/13/2019
by   Robi Bhattacharjee, et al.
0

We consider the problem of embedding a relation, represented as a directed graph, into Euclidean space. For three types of embeddings motivated by the recent literature on knowledge graphs, we obtain characterizations of which relations they are able to capture, as well as bounds on the minimal dimensionality and precision needed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/12/2022

Bending the Future: Autoregressive Modeling of Temporal Knowledge Graphs in Curvature-Variable Hyperbolic Spaces

Recently there is an increasing scholarly interest in time-varying knowl...
research
06/04/2020

Embedding Directed Graphs in Potential Fields Using FastMap-D

Embedding undirected graphs in a Euclidean space has many computational ...
research
05/23/2019

Multi-relational Poincaré Graph Embeddings

Hyperbolic embeddings have recently gained attention in machine learning...
research
09/29/2021

BiQUE: Biquaternionic Embeddings of Knowledge Graphs

Knowledge graph embeddings (KGEs) compactly encode multi-relational know...
research
02/12/2019

Hyperbolic Disk Embeddings for Directed Acyclic Graphs

Obtaining continuous representations of structural data such as directed...
research
10/28/2019

A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?

Knowledge Graphs (KGs) are composed of structured information about a pa...
research
10/09/2014

Realizing RCC8 networks using convex regions

RCC8 is a popular fragment of the region connection calculus, in which q...

Please sign up or login with your details

Forgot password? Click here to reset