paper-with-me

Papers

Directed Graph Embeddings in Pseudo-Riemannian Manifolds

2021-06-16 · Aaron Sim, Maciej Wiatrak, Angus Brayne, Páidí Creed, Saee Paliwal

The inductive biases of graph representation learning algorithms are often encoded in the background geometry of their embedding space. In this paper, we show that general directed graphs can be effectively represented by an embedding model that combines three components: a pseudo-Riemannian metric structure, a non-trivial global topology, and a unique likelihood function that explicitly incorporates a preferred direction in embedding space. We demonstrate the representational capabilities of this method by applying it to the task of link prediction on a series of synthetic and real directed graphs from natural language applications and biology. In particular, we show that low-dimensional cylindrical Minkowski and anti-de Sitter spacetimes can produce equal or better graph representations than curved Riemannian manifolds of higher dimensions.

📄 PDF Abstract BibTeX arXiv:2106.08678

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Representation LearningLink PredictionRepresentation Learning

Similar Papers 제목 키워드 기반

Pseudo-Riemannian Graph Convolutional Networks

2021-06-06 · Bo Xiong, Shichao Zhu, Nico Potyka, Shirui Pan 외

Graph convolutional networks (GCNs) are powerful frameworks for learning embeddings of graph-structured data. GCNs are traditionally studied through the lens of Euclidean geometry. Recent works find that non-Euclidean Ri…

Graph ReconstructionInductive BiasLink PredictionNode Classification

PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning

2025-12-09 · Ye Qin, Jingchao Wang, Yang Shi, Haiying Huang 외 arxiv

Capsule Networks (CapsNets) show exceptional graph representation capacity via dynamic routing and vectorized hierarchical representations, but they model the complex geometries of real\-world graphs poorly by fixed\-cur…

Graph Representation LearningGraph ClassificationGraph Learning

Pseudo-Riemannian Embedding Models for Multi-Relational Graph Representations

2022-12-02 · Saee Paliwal, Angus Brayne, Benedek Fabian, Maciej Wiatrak 외

In this paper we generalize single-relation pseudo-Riemannian graph embedding models to multi-relational networks, and show that the typical approach of encoding relations as manifold transformations translates from the …

Graph EmbeddingKnowledge Graph CompletionLink Prediction

Computationally Tractable Riemannian Manifolds for Graph Embeddings

2020-02-20 · Calin Cruceru, Gary Bécigneul, Octavian-Eugen Ganea

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 bene…

BIG-bench Machine Learning

Ultrahyperbolic Knowledge Graph Embeddings

2022-06-01 · Bo Xiong, Shichao Zhu, Mojtaba Nayyeri, Chengjin Xu 외

Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies. The topological structures of real-world KGs, however, are rather heterogeneou…

Knowledge Graph Embeddings