Embedding Knowledge Graphs in Degenerate Clifford Algebras

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Teyou, Louis Mozart Kamdem, Demir, Caglar, Ngomo, Axel-Cyrille Ngonga
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912040616984576
author Teyou, Louis Mozart Kamdem
Demir, Caglar
Ngomo, Axel-Cyrille Ngonga
author_facet Teyou, Louis Mozart Kamdem
Demir, Caglar
Ngomo, Axel-Cyrille Ngonga
contents Clifford algebras are a natural generalization of the real numbers, the complex numbers, and the quaternions. So far, solely Clifford algebras of the form $Cl_{p,q}$ (i.e., algebras without nilpotent base vectors) have been studied in the context of knowledge graph embeddings. We propose to consider nilpotent base vectors with a nilpotency index of two. In these spaces, denoted $Cl_{p,q,r}$, allows generalizing over approaches based on dual numbers (which cannot be modelled using $Cl_{p,q}$) and capturing patterns that emanate from the absence of higher-order interactions between real and complex parts of entity embeddings. We design two new models for the discovery of the parameters $p$, $q$, and $r$. The first model uses a greedy search to optimize $p$, $q$, and $r$. The second predicts $(p, q,r)$ based on an embedding of the input knowledge graph computed using neural networks. The results of our evaluation on seven benchmark datasets suggest that nilpotent vectors can help capture embeddings better. Our comparison against the state of the art suggests that our approach generalizes better than other approaches on all datasets w.r.t. the MRR it achieves on validation data. We also show that a greedy search suffices to discover values of $p$, $q$ and $r$ that are close to optimal.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04870
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Embedding Knowledge Graphs in Degenerate Clifford Algebras
Teyou, Louis Mozart Kamdem
Demir, Caglar
Ngomo, Axel-Cyrille Ngonga
Artificial Intelligence
Machine Learning
Clifford algebras are a natural generalization of the real numbers, the complex numbers, and the quaternions. So far, solely Clifford algebras of the form $Cl_{p,q}$ (i.e., algebras without nilpotent base vectors) have been studied in the context of knowledge graph embeddings. We propose to consider nilpotent base vectors with a nilpotency index of two. In these spaces, denoted $Cl_{p,q,r}$, allows generalizing over approaches based on dual numbers (which cannot be modelled using $Cl_{p,q}$) and capturing patterns that emanate from the absence of higher-order interactions between real and complex parts of entity embeddings. We design two new models for the discovery of the parameters $p$, $q$, and $r$. The first model uses a greedy search to optimize $p$, $q$, and $r$. The second predicts $(p, q,r)$ based on an embedding of the input knowledge graph computed using neural networks. The results of our evaluation on seven benchmark datasets suggest that nilpotent vectors can help capture embeddings better. Our comparison against the state of the art suggests that our approach generalizes better than other approaches on all datasets w.r.t. the MRR it achieves on validation data. We also show that a greedy search suffices to discover values of $p$, $q$ and $r$ that are close to optimal.
title Embedding Knowledge Graphs in Degenerate Clifford Algebras
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.04870