RelBall: Relation Ball with Quaternion Rotation for Knowledge Graph Completion

• URL: http://arxiv.org/abs/2606.27967v1
• Date: Fri, 26 Jun 2026 11:15:50 GMT
• Title: RelBall: Relation Ball with Quaternion Rotation for Knowledge Graph Completion
• Abstract summary: Real-world knowledge graphs are often incomplete, lacking many valid facts. Knowledge Graph Completion aims to predict missing links using known triples.<n>Key challenge is modeling diverse relational patterns such as symmetry, antisymmetry, inversion, composition and semantic hierarchy.<n>We propose RelBall, which extends Rotate3D with two innovations.
• Score: 6.291655897444824
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world knowledge graphs are often incomplete, lacking many valid facts. Knowledge Graph Completion (KGC) aims to predict missing links using known triples, thereby enhancing graph coverage. A key challenge is modeling diverse relational patterns such as symmetry, antisymmetry, inversion, composition and semantic hierarchy. Existing models such as RotatE can capture symmetric, antisymmetric, inverse, and commutative composition patterns, yet struggle with non-commutative composition. Rotate3D addresses this by introducing non-commutativity via three-dimensional rotations, but still fails to capture the semantic hierarchies prevalent in knowledge graphs. Moreover, both models cannot effectively model one-to-many relations. To overcome these limitations, we propose RelBall, which extends Rotate3D with two innovations. First, our model introduces modulus transformation to model hierarchies, driving abstract concepts toward smaller moduli and concrete instances toward larger ones. Second, it introduces a tail-centric relation ball to model one-to-one, one-to-many, many-to-one, and many-to-many relations. RelBall offers the following advantages: (1) coverage of all relational patterns, including the ones mentioned above; (2) an interpretable hierarchical representation where the modulus directly reflect semantic levels; (3) support for one-to-one, one-to-many, many-to-one, and many-to-many relations. Experiments on multiple datasets demonstrate RelBall's competitive link prediction performance against various baselines.

Related papers

• SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D [51.32219731589742]
  3D scene graphs provide a structured representation of object entities and their relationships.<n>Existing approaches for 3D scene graph generation typically combine scene reconstruction with graph neural networks (GNNs)<n>In this work, we introduce a Scene Graph Retrieval-Reasoning Model in 3D (SGR3 Model)
  arXiv  Detail & Related papers  (2026-03-04T21:19:54Z)
• Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls [54.57326125204404]
  Language models are increasingly capable, yet still fail at a seemingly simple task of multi-digit multiplication.<n>We study why, by reverse-engineering a model that successfully learns multiplication via emphimplicit chain-of-thought'
  arXiv  Detail & Related papers  (2025-09-30T19:03:26Z)
• Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation [12.69417276887153]
  Quaternion contains one real part and three imaginary parts, which provided a more expressive hypercomplex space for learning knowledge graph.<n>Existing quaternion embedding models measure the plausibility of a triplet either through semantic matching or geometric distance scoring functions.<n>We propose a novel quaternion knowledge graph embedding model that combines semantic matching with entity's geometric distance to better measure the plausibility of triplets.
  arXiv  Detail & Related papers  (2024-12-05T11:17:03Z)
• SpherE: Expressive and Interpretable Knowledge Graph Embedding for Set Retrieval [40.250677256048576]
  We show that the set retrieval highly depends on expressive modeling of many-to-many relations. We propose a new KG embedding model SpherE to address this problem. Our SpherE can more expressively model one-to-many, many-to-one, and many-to-many relations.
  arXiv  Detail & Related papers  (2024-04-29T22:21:24Z)
• Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks [58.43972540643903]
  We propose HyperGraph neural network for ERE ($hgnn$), which is built upon the PL-marker (a state-of-the-art marker-based pipleline model) To alleviate error propagation,we use a high-recall pruner mechanism to transfer the burden of entity identification and labeling from the NER module to the joint module of our model. Experiments on three widely used benchmarks for ERE task show significant improvements over the previous state-of-the-art PL-marker.
  arXiv  Detail & Related papers  (2023-10-26T08:36:39Z)
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models [7.620967781722715]
  Knowledge graph embeddings map nodes into a vector space to predict new links, scoring them according to geometric criteria. No single model can learn all patterns equally well. In this paper, we combine the query representations from several models in a unified one to incorporate patterns that are independently captured by each model.
  arXiv  Detail & Related papers  (2023-02-13T10:07:26Z)
• GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
  We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
  arXiv  Detail & Related papers  (2022-12-01T11:49:07Z)
• A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach [59.89749342550104]
  We propose the task of hyper-relational extraction to extract more specific and complete facts from text. Existing models cannot perform hyper-relational extraction as it requires a model to consider the interaction between three entities. We propose CubeRE, a cube-filling model inspired by table-filling approaches and explicitly considers the interaction between relation triplets and qualifiers.
  arXiv  Detail & Related papers  (2022-11-18T03:51:28Z)
• Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones [64.75766944882389]
  We present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph. In particular, ConE uses cone containment constraints in different subspaces of the hyperbolic embedding space to capture multiple heterogeneous hierarchies. Our approach yields new state-of-the-art Hits@1 of 45.3% on WN18RR and 16.1% on DDB14 (0.231 MRR)
  arXiv  Detail & Related papers  (2021-10-28T07:16:08Z)
• QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion [4.837804582368272]
  We propose a novel model, QuatDE, with a dynamic mapping strategy to explicitly capture a variety of relational patterns. Experiment results show QuatDE achieves state-of-the-art performance on three well-established knowledge graph completion benchmarks.
  arXiv  Detail & Related papers  (2021-05-19T09:10:39Z)
• LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction [7.0294164380111015]
  We propose a novel embedding model, namely LineaRE, which is capable of modeling four connectivity patterns and four mapping properties. Experimental results on multiple widely used real-world datasets show that the proposed LineaRE model significantly outperforms existing state-of-the-art models for link prediction tasks.
  arXiv  Detail & Related papers  (2020-04-21T14:19:43Z)

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.