THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs

• URL: http://arxiv.org/abs/2602.05424v2
• Date: Fri, 06 Feb 2026 01:44:41 GMT
• Title: THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs
• Authors: Weijian Yu, Yuhuan Lu, Dingqi Yang,
• Abstract summary: We propose THOR, an inducTive link prediction technique for Hyper-relational knOwledge gRaphs.<n> THOR is designed to learn from the two foundation graphs with two parallel graph encoders followed by a transformer decoder.<n>Results show that THOR outperforms a sizable collection of baselines, yielding 66.1%, 55.9%, and 20.4% improvement over the best-performing rule-based, semi-inductive, and fully-inductive techniques, respectively.
• Score: 15.89751830563422
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge graphs (KGs) have become a key ingredient supporting a variety of applications. Beyond the traditional triplet representation of facts where a relation connects two entities, modern KGs observe an increasing number of hyper-relational facts, where an arbitrary number of qualifiers associated with a triplet provide auxiliary information to further describe the rich semantics of the triplet, which can effectively boost the reasoning performance in link prediction tasks. However, existing link prediction techniques over such hyper-relational KGs (HKGs) mostly focus on a transductive setting, where KG embedding models are learned from the specific vocabulary of a given KG and subsequently can only make predictions within the same vocabulary, limiting their generalizability to previously unseen vocabularies. Against this background, we propose THOR, an inducTive link prediction technique for Hyper-relational knOwledge gRaphs. Specifically, we first introduce both relation and entity foundation graphs, modeling their fundamental inter- and intra-fact interactions in HKGs, which are agnostic to any specific relations and entities. Afterward, THOR is designed to learn from the two foundation graphs with two parallel graph encoders followed by a transformer decoder, which supports efficient masked training and fully-inductive inference. We conduct a thorough evaluation of THOR in hyper-relational link prediction tasks on 12 datasets with different settings. Results show that THOR outperforms a sizable collection of baselines, yielding 66.1%, 55.9%, and 20.4% improvement over the best-performing rule-based, semi-inductive, and fully-inductive techniques, respectively. A series of ablation studies also reveals our key design factors capturing the structural invariance transferable across HKGs for inductive tasks.

Related papers

• Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs [55.918039693545616]
  We introduce a novel method, named Context Pooling, to enhance GNN-based models' efficacy for link predictions in Knowledge Graphs.<n>Our method is generic and assessed by being applied to two state-of-the-art (SOTA) models on three public transductive and inductive datasets.
  arXiv  Detail & Related papers  (2025-07-10T09:54:37Z)
• Efficient Relational Context Perception for Knowledge Graph Completion [25.903926643251076]
  Knowledge Graphs (KGs) provide a structured representation of knowledge but often suffer from challenges of incompleteness.<n>Previous knowledge graph embedding models are limited in their ability to capture expressive features.<n>We propose Triple Receptance Perception architecture to model sequential information, enabling the learning of dynamic context.
  arXiv  Detail & Related papers  (2024-12-31T11:25:58Z)
• A Relation-Interactive Approach for Message Passing in Hyper-relational Knowledge Graphs [0.0]
  We propose a message-passing-based graph encoder with global relation structure awareness ability, which we call ReSaE. Our experiments demonstrate that ReSaE achieves state-of-the-art performance on multiple link prediction benchmarks.
  arXiv  Detail & Related papers  (2024-02-23T06:55:04Z)
• Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction [121.65152276851619]
  We show that semantic correlations between relations are inherently edge-level and entity-independent. We propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph.
  arXiv  Detail & Related papers  (2023-09-20T08:11:58Z)
• Pre-training Transformers for Knowledge Graph Completion [81.4078733132239]
  We introduce a novel inductive KG representation model (iHT) for learning transferable representation for knowledge graphs. iHT consists of a entity encoder (e.g., BERT) and a neighbor-aware relational scoring function both parameterized by Transformers. Our approach achieves new state-of-the-art results on matched evaluations, with a relative improvement of more than 25% in mean reciprocal rank over previous SOTA models.
  arXiv  Detail & Related papers  (2023-03-28T02:10:37Z)
• Multi-Aspect Explainable Inductive Relation Prediction by Sentence Transformer [60.75757851637566]
  We introduce the concepts of relation path coverage and relation path confidence to filter out unreliable paths prior to model training to elevate the model performance. We propose Knowledge Reasoning Sentence Transformer (KRST) to predict inductive relations in knowledge graphs.
  arXiv  Detail & Related papers  (2023-01-04T15:33:49Z)
• Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network [111.67744771462873]
  This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs) It combines high-order reasoning into a graph convolutional network, namely HoGRN. It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
  arXiv  Detail & Related papers  (2022-07-14T10:16:56Z)
• ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion [78.8942067357231]
  ExpressivE embeds pairs of entities as points and relations as hyper-parallelograms in the virtual triple space. We show that ExpressivE is competitive with state-of-the-art KGEs and even significantly outperforms them on W18RR.
  arXiv  Detail & Related papers  (2022-06-08T23:34:39Z)
• Improving Inductive Link Prediction Using Hyper-Relational Facts [15.820005235333882]
  We study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by graph neural networks. Our experiments show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains.
  arXiv  Detail & Related papers  (2021-07-10T19:16:03Z)
• Improving Hyper-Relational Knowledge Graph Completion [35.487553537419224]
  Hyper-relational KGs (HKGs) allow triplets to be associated with additional relation-entity pairs (a.k.a qualifiers) to convey more complex information. How to effectively and efficiently model the triplet-qualifier relationship for prediction tasks such as HKG completion is an open challenge for research. This paper proposes to improve the best-performing method in HKG completion, namely STARE, by introducing two novel revisions.
  arXiv  Detail & Related papers  (2021-04-16T15:26:41Z)
• Message Passing for Hyper-Relational Knowledge Graphs [7.733963597282456]
  We propose a message passing graph encoder - StarE capable of modeling such hyper-relational knowledge graphs. StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks.
  arXiv  Detail & Related papers  (2020-09-22T22:38:54Z)

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.