Feature Propagation on Knowledge Graphs using Cellular Sheaves

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cobb, John, Gebhart, Thomas
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908769104953344
author Cobb, John
Gebhart, Thomas
author_facet Cobb, John
Gebhart, Thomas
contents Many inference tasks on knowledge graphs, including relation prediction, operate on knowledge graph embeddings -- vector representations of the vertices (entities) and edges (relations) that preserve task-relevant structure encoded within the underlying combinatorial object. Such knowledge graph embeddings can be modeled as an approximate global section of a cellular sheaf, an algebraic structure over the graph. Using the diffusion dynamics encoded by the corresponding sheaf Laplacian, we optimally propagate known embeddings of a subgraph to inductively represent new entities introduced into the knowledge graph at inference time. We implement this algorithm via an efficient iterative scheme and show that on a number of large-scale knowledge graph embedding benchmarks, our method is competitive with -- and in some scenarios outperforms -- more complex models derived explicitly for inductive knowledge graph reasoning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2309_03773
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Feature Propagation on Knowledge Graphs using Cellular Sheaves
Cobb, John
Gebhart, Thomas
Artificial Intelligence
Information Retrieval
Social and Information Networks
Many inference tasks on knowledge graphs, including relation prediction, operate on knowledge graph embeddings -- vector representations of the vertices (entities) and edges (relations) that preserve task-relevant structure encoded within the underlying combinatorial object. Such knowledge graph embeddings can be modeled as an approximate global section of a cellular sheaf, an algebraic structure over the graph. Using the diffusion dynamics encoded by the corresponding sheaf Laplacian, we optimally propagate known embeddings of a subgraph to inductively represent new entities introduced into the knowledge graph at inference time. We implement this algorithm via an efficient iterative scheme and show that on a number of large-scale knowledge graph embedding benchmarks, our method is competitive with -- and in some scenarios outperforms -- more complex models derived explicitly for inductive knowledge graph reasoning tasks.
title Feature Propagation on Knowledge Graphs using Cellular Sheaves
topic Artificial Intelligence
Information Retrieval
Social and Information Networks
url https://arxiv.org/abs/2309.03773