aiqbench analysis
This arXiv preprint proposes a method for predicting missing links in knowledge graphs when the entities and relations were not seen during training. It models logical rules as hyperedges, which can capture multi-relation dependencies that pairwise relation graphs miss. The reported gains rest on the authors' own benchmark comparisons, so readers should check the baselines and evaluation setup before judging how much the approach advances the state of the art.
QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
arXiv:2610.18198v1 Announce Type: new Abstract: Knowledge graph link prediction involving unseen entities and relations requires learning transferable reasoning patterns from observed graph structure. Existing methods based on relation graphs primarily capture pairwise dependencies, limiting their ability to preserve the compositional semantics, relation ordering, and role information of complete path rules. To address this limitation, we propose QORH (Query-specific Ordered Rule Hypergraph), which jointly encodes rule heads and ordered rule bodies as hyperedges conditioned on the query relation, explicitly modeling joint dependencies among multiple relations. QORH performs learnable rule selection using statistical evidence, such as rule confidence and coverage, and enhances relation representations through role-aware hypergraph message passing to guide entity-level reasoning. The model's shared parameters are independent of specific entity or relation identifiers, enabling inductive prediction for unseen entities and relations. Extensive experiments on entity-inductive and fully inductive benchmarks demonstrate that QORH significantly outperforms the state-of-the-art baselines included in our evaluation, validating the effectiveness of rule hypergraph modeling for inductive link prediction.
Abstract:Knowledge graph link prediction involving unseen entities and relations requires learning transferable reasoning patterns from observed graph structure. Existing methods based on relation graphs primarily capture pairwise dependencies, limiting their ability to preserve the compositional semantics, relation ordering, and role information of complete path rules. To address this limitation, we propose QORH (Query-specific Ordered Rule Hypergraph), which jointly encodes rule heads and ordered rule bodies as hyperedges conditioned on the query relation, explicitly modeling joint dependencies among multiple relations. QORH performs learnable rule selection using statistical evidence, such as rule confidence and coverage, and enhances relation representations through role-aware hypergraph message passing to guide entity-level reasoning. The model's shared parameters are independent of specific entity or relation identifiers, enabling inductive prediction for unseen entities and relations. Extensive experiments on entity-inductive and fully inductive benchmarks demonstrate that QORH significantly outperforms the state-of-the-art baselines included in our evaluation, validating the effectiveness of rule hypergraph modeling for inductive link prediction.
Artificial Intelligence (cs.AI)
arXiv:2610.18198 [cs.AI]
(or arXiv:2610.18198v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.18198 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
Related coverage
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026
Deconfusing Corrigibility
AI Alignment Forum · Oct 17, 2026
Granite 4.1 LLMs: How They’re Built
Hugging Face · Apr 29, 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026