arXiv：cs.AI· Naixing Xu·· 17 小时前
QORH：面向归纳式知识图谱链接预测的查询特定有序规则超图
QORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
AI 导读
研究者提出 QORH（Query-specific Ordered Rule Hypergraph），将规则头和有序规则体以超边形式联合编码，显式建模多关系间的联合依赖。该模型通过规则置信度、覆盖率等统计证据进行可学习规则选择，并用角色感知的超图消息传递增强关系表示。在实体归纳与完全归纳基准上，QORH 显著优于所评估的 SOTA 基线。
正文
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18198 [cs.AI] |
| (or arXiv:2610.18198v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18198 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Naixing Xu [view email]
[v1]
Tue, 13 Oct 2026 11:35:35 UTC (1,822 KB)
来源：arXiv：cs.AI · arxiv.org