HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gajjar, Jugal, Ranaware, Kaustik, Subramaniakuppusamy, Kamalasankari, Gandhi, Vaibhav
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912707587866624
author Gajjar, Jugal
Ranaware, Kaustik
Subramaniakuppusamy, Kamalasankari
Gandhi, Vaibhav
author_facet Gajjar, Jugal
Ranaware, Kaustik
Subramaniakuppusamy, Kamalasankari
Gandhi, Vaibhav
contents Knowledge graphs have emerged as fundamental structures for representing complex relational data across scientific and enterprise domains. However, existing embedding methods face critical limitations when modeling diverse relationship types at scale: Euclidean models struggle with hierarchies, vector space models cannot capture asymmetry, and hyperbolic models fail on symmetric relations. We propose HyperComplEx, a hybrid embedding framework that adaptively combines hyperbolic, complex, and Euclidean spaces via learned attention mechanisms. A relation-specific space weighting strategy dynamically selects optimal geometries for each relation type, while a multi-space consistency loss ensures coherent predictions across spaces. We evaluate HyperComplEx on computer science research knowledge graphs ranging from 1K papers (~25K triples) to 10M papers (~45M triples), demonstrating consistent improvements over state-of-the-art baselines including TransE, RotatE, DistMult, ComplEx, SEPA, and UltraE. Additional tests on standard benchmarks confirm significantly higher results than all baselines. On the 10M-paper dataset, HyperComplEx achieves 0.612 MRR, a 4.8% relative gain over the best baseline, while maintaining efficient training, achieving 85 ms inference per triple. The model scales near-linearly with graph size through adaptive dimension allocation. We release our implementation and dataset family to facilitate reproducible research in scalable knowledge graph embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10842
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings
Gajjar, Jugal
Ranaware, Kaustik
Subramaniakuppusamy, Kamalasankari
Gandhi, Vaibhav
Artificial Intelligence
Databases
Machine Learning
Social and Information Networks
Knowledge graphs have emerged as fundamental structures for representing complex relational data across scientific and enterprise domains. However, existing embedding methods face critical limitations when modeling diverse relationship types at scale: Euclidean models struggle with hierarchies, vector space models cannot capture asymmetry, and hyperbolic models fail on symmetric relations. We propose HyperComplEx, a hybrid embedding framework that adaptively combines hyperbolic, complex, and Euclidean spaces via learned attention mechanisms. A relation-specific space weighting strategy dynamically selects optimal geometries for each relation type, while a multi-space consistency loss ensures coherent predictions across spaces. We evaluate HyperComplEx on computer science research knowledge graphs ranging from 1K papers (~25K triples) to 10M papers (~45M triples), demonstrating consistent improvements over state-of-the-art baselines including TransE, RotatE, DistMult, ComplEx, SEPA, and UltraE. Additional tests on standard benchmarks confirm significantly higher results than all baselines. On the 10M-paper dataset, HyperComplEx achieves 0.612 MRR, a 4.8% relative gain over the best baseline, while maintaining efficient training, achieving 85 ms inference per triple. The model scales near-linearly with graph size through adaptive dimension allocation. We release our implementation and dataset family to facilitate reproducible research in scalable knowledge graph embeddings.
title HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings
topic Artificial Intelligence
Databases
Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2511.10842