HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings

• URL: http://arxiv.org/abs/2511.10842v1
• Date: Thu, 13 Nov 2025 23:06:06 GMT
• Title: HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings
• Authors: Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy, Vaibhav Gandhi,
• Abstract summary: HyperComplEx is a hybrid embedding framework that combines hyperbolic, complex, and Euclidean spaces via learned attention mechanisms.<n>A relation-specific space weighting strategy dynamically selects optimal geometries for each relation type.<n>On the 10M-paper dataset, HyperComplEx achieves 0.612 MRR, a 4.8% relative gain over the best baseline.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts [20.82313207866023]
  We propose a unified framework that leverages multiple geometric spaces simultaneously to learn curvature-aware representations.<n>We develop MoSLoRA, which extends Low-Rank Adaptation (LoRA) with heterogeneous geometric experts.<n>Our experiments across diverse benchmarks demonstrate that MoSLoRA consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-02-16T06:07:32Z)
• SKGE: Spherical Knowledge Graph Embedding with Geometric Regularization [0.0]
  We propose Spherical Knowledge Graph Embedding (SKGE), a model that constrains entity representations to a compact manifold: a hypersphere.<n>We demonstrate that SKGE consistently and significantly outperforms its strong Euclidean counterpart, TransE.
  arXiv  Detail & Related papers  (2025-11-04T10:40:46Z)
• Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining [59.369484219304866]
  We conduct an unprecedented empirical investigation training over 3,700 Large Language Models (LLMs) from scratch across 100 trillion tokens.<n>We establish a universal Scaling Law for hyperparameter optimization in LLM Pre-training, called Step Law.<n>Our estimated optima deviates from the global best performance found via exhaustive search by merely 0.094% on the test set.
  arXiv  Detail & Related papers  (2025-03-06T18:58:29Z)
• HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration [60.01977041900338]
  HyperGCT is a flexible dynamic Hyper-GNN-learned geometric ConstrainT.<n>It mines robust geometric constraints from dynamic hypergraphs for 3D registration.<n>Experiments on 3DMatch, 3DLoMatch, KITTI-LC, and ETH show that HyperGCT achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-04T02:05:43Z)
• From Semantics to Hierarchy: A Hybrid Euclidean-Tangent-Hyperbolic Space Model for Temporal Knowledge Graph Reasoning [1.1372536310854844]
  Temporal knowledge graph (TKG) reasoning predicts future events based on historical data. Existing Euclidean models excel at capturing semantics but struggle with hierarchy. We propose a novel hybrid geometric space approach that leverages the strengths of both Euclidean and hyperbolic models.
  arXiv  Detail & Related papers  (2024-08-30T10:33:08Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System [18.07821800367287]
  We present a web-scale Adaptive Mixed-Curvature ADvertisement retrieval system (AMCAD) to automatically capture the complex and heterogeneous graph structures in non-Euclidean spaces. To deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework.
  arXiv  Detail & Related papers  (2022-03-28T12:29:30Z)
• Hyperbolic Graph Neural Networks: A Review of Methods and Applications [61.49208407567829]
  This survey paper provides a comprehensive review of the rapidly evolving field of Hyperbolic Graph Learning (HGL)<n>We systematically categorize and analyze existing methods dividing them into (1) hyperbolic graph embedding-based techniques, (2) graph neural network-based hyperbolic models, and (3) emerging paradigms.<n>We extensively discuss diverse applications of HGL across multiple domains, including recommender systems, knowledge graphs, bioinformatics, and other relevant scenarios.
  arXiv  Detail & Related papers  (2022-02-28T15:08:48Z)
• Hermitian Symmetric Spaces for Graph Embeddings [0.0]
  We learn continuous representations of graphs in spaces of symmetric matrices over C. These spaces offer a rich geometry that simultaneously admits hyperbolic and Euclidean subspaces. The proposed models are able to automatically adapt to very dissimilar arrangements without any apriori estimates of graph features.
  arXiv  Detail & Related papers  (2021-05-11T18:14:52Z)
• Spatial-Spectral Clustering with Anchor Graph for Hyperspectral Image [88.60285937702304]
  This paper proposes a novel unsupervised approach called spatial-spectral clustering with anchor graph (SSCAG) for HSI data clustering. The proposed SSCAG is competitive against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-24T08:09:27Z)
• Knowledge Generation -- Variational Bayes on Knowledge Graphs [0.685316573653194]
  This thesis is a proof of concept for potential of Vari Auto-Encoder (VAE) on representation of real-world Knowledge Graphs. Inspired by successful approaches to generation graphs, we evaluate the capabilities of our model, the Variational Auto-Encoder (RGVAE) The RGVAE is first evaluated on link prediction. The mean reciprocal rank (MRR) scores on the two FB15K-237 and WN18RR datasets are compared. We investigate the latent space in a twofold experiment: first, linear between the latent representation of two triples, then the exploration of each
  arXiv  Detail & Related papers  (2021-01-21T21:23:17Z)
• Mix Dimension in Poincar\'{e} Geometry for 3D Skeleton-based Action Recognition [57.98278794950759]
  Graph Convolutional Networks (GCNs) have already demonstrated their powerful ability to model the irregular data. We present a novel spatial-temporal GCN architecture which is defined via the Poincar'e geometry. We evaluate our method on two current largest scale 3D datasets.
  arXiv  Detail & Related papers  (2020-07-30T18:23:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.