Log In Sign Up

Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach

by   Federico López, et al.

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.


page 1

page 2

page 26


Hermitian Symmetric Spaces for Graph Embeddings

Learning faithful graph representations as sets of vertex embeddings has...

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

There has recently been increasing interest in learning representations ...

Efficient Representation Learning Using Random Walks for Dynamic graphs

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

Heterogeneous manifolds for curvature-aware graph embedding

Graph embeddings, wherein the nodes of the graph are represented by poin...

On the Equivalence between Node Embeddings and Structural Graph Representations

This work provides the first unifying theoretical framework for node emb...

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

Feature ranking has been widely adopted in machine learning applications...

Set2Box: Similarity Preserving Representation Learning of Sets

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