HYPER模型可预测新实体和新关系的超图链接，支持任意复杂关系泛化。
HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs
- 通过编码超边中实体及其位置，实现对不同阶数关系的统一建模。
- 在16个新构建的数据集上，性能全面超越现有方法，尤其在高阶关系上优势显著。
- 适合需要跨关系类型、跨实体泛化的知识超图应用开发者使用。
基于知识超图的归纳式链接预测任务旨在预测包含完全新实体（即训练中未见节点）的缺失超边。现有方法假设关系词汇表固定，因此无法推广到包含新关系类型（即训练中未见的关系）的知识超图。受知识图谱基础模型启发，我们提出HYPER，一个面向链接预测的基础模型，能够泛化至任意知识超图，包括新实体与新关系。重要的是，HYPER可通过编码每个超边中实体及其位置，学习并迁移不同阶数的关系类型。为评估HYPER，我们从现有知识超图构建了16个新的归纳式数据集，涵盖多样化的不同阶数关系类型。实验表明，无论是在仅节点归纳还是节点与关系联合归纳设置下，HYPER均持续优于所有现有方法，展现出对未见高阶关系结构的强大泛化能力。
原文摘要 · Abstract (English)
Inductive link prediction with knowledge hypergraphs is the task of predicting missing hyperedges involving completely novel entities (i.e., nodes unseen during training). Existing methods for inductive link prediction with knowledge hypergraphs assume a fixed relational vocabulary and, as a result, cannot generalize to knowledge hypergraphs with novel relation types (i.e., relations unseen during training). Inspired by knowledge graph foundation models, we propose HYPER as a foundation model for link prediction, which can generalize to any knowledge hypergraph, including novel entities and novel relations. Importantly, HYPER can learn and transfer across different relation types of varying arities, by encoding the entities of each hyperedge along with their respective positions in the hyperedge. To evaluate HYPER, we construct 16 new inductive datasets from existing knowledge hypergraphs, covering a diverse range of relation types of varying arities. Empirically, HYPER consistently outperforms all existing methods in both node-only and node-and-relation inductive settings, showing strong generalization to unseen, higher-arity relational structures.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。