DeepAI
Log In Sign Up

Computationally Tractable Riemannian Manifolds for Graph Embeddings

02/20/2020
by   Calin Cruceru, et al.
0

Representing graphs as sets of node embeddings in certain curved Riemannian manifolds has recently gained momentum in machine learning due to their desirable geometric inductive biases, e.g., hierarchical structures benefit from hyperbolic geometry. However, going beyond embedding spaces of constant sectional curvature, while potentially more representationally powerful, proves to be challenging as one can easily lose the appeal of computationally tractable tools such as geodesic distances or Riemannian gradients. Here, we explore computationally efficient matrix manifolds, showcasing how to learn and optimize graph embeddings in these Riemannian spaces. Empirically, we demonstrate consistent improvements over Euclidean geometry while often outperforming hyperbolic and elliptical embeddings based on various metrics that capture different graph properties. Our results serve as new evidence for the benefits of non-Euclidean embeddings in machine learning pipelines.

READ FULL TEXT

page 21

page 25

06/06/2021

Semi-Riemannian Graph Convolutional Networks

Graph Convolutional Networks (GCNs) are typically studied through the le...
02/02/2022

Heterogeneous manifolds for curvature-aware graph embedding

Graph embeddings, wherein the nodes of the graph are represented by poin...
05/11/2020

Design and visualization of Riemannian metrics

Local and global illumination were recently defined in Riemannian manifo...
05/11/2021

Hermitian Symmetric Spaces for Graph Embeddings

Learning faithful graph representations as sets of vertex embeddings has...
12/11/2018

Adversarial Autoencoders with Constant-Curvature Latent Manifolds

Constant-curvature Riemannian manifolds (CCMs) have been shown to be ide...
07/02/2019

Learning graph-structured data using Poincaré embeddings and Riemannian K-means algorithms

Recent literature has shown several benefits of hyperbolic embedding of ...
10/09/2020

Conformal retrofitting via Riemannian manifolds: distilling task-specific graphs into pretrained embeddings

Pretrained (language) embeddings are versatile, task-agnostic feature re...