DeepAI
Log In Sign Up

Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach

06/09/2021
by   Federico López, et al.
0

Learning faithful graph representations as sets of vertex embeddings has become a fundamental intermediary step in a wide range of machine learning applications. We propose the systematic use of symmetric spaces in representation learning, a class encompassing many of the previously used embedding targets. This enables us to introduce a new method, the use of Finsler metrics integrated in a Riemannian optimization scheme, that better adapts to dissimilar structures in the graph. We develop a tool to analyze the embeddings and infer structural properties of the data sets. For implementation, we choose Siegel spaces, a versatile family of symmetric spaces. Our approach outperforms competitive baselines for graph reconstruction tasks on various synthetic and real-world datasets. We further demonstrate its applicability on two downstream tasks, recommender systems and node classification.

READ FULL TEXT

page 1

page 2

page 26

05/11/2021

Hermitian Symmetric Spaces for Graph Embeddings

Learning faithful graph representations as sets of vertex embeddings has...
11/08/2020

DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion

There has recently been increasing interest in learning representations ...
01/05/2019

Efficient Representation Learning Using Random Walks for Dynamic graphs

An important part of many machine learning workflows on graphs is vertex...
02/02/2022

Heterogeneous manifolds for curvature-aware graph embedding

Graph embeddings, wherein the nodes of the graph are represented by poin...
10/01/2019

On the Equivalence between Node Embeddings and Structural Graph Representations

This work provides the first unifying theoretical framework for node emb...
01/23/2021

ReliefE: Feature Ranking in High-dimensional Spaces via Manifold Embeddings

Feature ranking has been widely adopted in machine learning applications...
10/07/2022

Set2Box: Similarity Preserving Representation Learning of Sets

Sets have been used for modeling various types of objects (e.g., a docum...