用预训练语言模型补全缺失类型信息，提升新实体链接预测效果
Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models
- 用PLM挖掘节点的隐式类型语义，不依赖显式类型标签
- 在类型信息少、图连接稀疏时性能超越现有方法
- 适合处理真实世界中类型缺失或粗糙的知识图谱
归纳式链接预测正成为现实知识图谱的关键范式，新实体频繁出现，模型需在不重新训练的情况下泛化。预测链接面临挑战：需利用子图结构、类型注释和本体约束等通用节点特征，推测未见过的实体。然而，显式类型信息常缺失或不完整，且多数知识图谱中的类型标注粗粒度、稀疏且易出错。本文探索预训练语言模型（PLM）在节点表征中注入隐式类型信号的潜力，提出TyleR——一种无需显式类型但具备类型感知能力的子图归纳式链接预测方法。实验表明，在类型标注稀缺和图连通性低的场景下，TyleR显著优于现有最优基线。代码已开源：https://github.com/sisinflab/tyler。
原文摘要 · Abstract (English)
Inductive link prediction is emerging as a key paradigm for real-world knowledge graphs (KGs), where new entities frequently appear and models must generalize to them without retraining. Predicting links in a KG faces the challenge of guessing previously unseen entities by leveraging generalizable node features such as subgraph structure, type annotations, and ontological constraints. However, explicit type information is often lacking or incomplete. Even when available, type information in most KGs is often coarse-grained, sparse, and prone to errors due to human annotation. In this work, we explore the potential of pre-trained language models (PLMs) to enrich node representations with implicit type signals. We introduce TyleR, a Type-less yet type-awaRe approach for subgraph-based inductive link prediction that leverages PLMs for semantic enrichment. Experiments on standard benchmarks demonstrate that TyleR outperforms state-of-the-art baselines in scenarios with scarce type annotations and sparse graph connectivity. To ensure reproducibility, we share our code at https://github.com/sisinflab/tyler .
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。