首个支持跨领域时间知识图谱推理的模型，不依赖预定义词汇表。
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
- 用相对时间关系编码替代绝对时间，捕捉谓词间的交互模式。
- 在6个不同领域数据集上实现跨图迁移，性能优于现有方法。
- 适合处理异构、未知实体与关系的开放域知识图谱推理。
时间知识图谱是语义网应用的核心，但现有补全方法假设训练时已知实体、关系名和时间戳，导致模型仅限于单一图谱与词汇表。我们提出FITTER，首个完全归纳式的时间知识图谱链接预测结构化模型，支持跨领域迁移：推理图可包含完全未见过的实体、关系名和时间戳，来自不同领域。FITTER通过相对而非绝对排序的编码表示每个谓词与其余谓词及时间的交互模式；消息传递融合局部与全局时间上下文，生成词汇无关嵌入。我们证明该时间编码具有时间平移不变性，并在六个涵盖不同领域、粒度与时间跨度的时间知识图谱基准上评估了跨图、跨领域迁移性能。FITTER在无需重训练的情况下持续优于归纳基线，表明词汇无关的结构学习是语义网异构知识图谱推理的可行基础。
原文摘要 · Abstract (English)
Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned about are already known at training time, restricting each model to a single graph and vocabulary. We propose FITTER, the first fully-inductive structural model for temporal knowledge graph link prediction that supports cross-domain transfer: the inference graph may contain entirely unseen entities, relation names, and timestamps drawn from a different domain. FITTER represents each predicate by its interaction patterns with others and time through encodings of relative rather than absolute ordering; message-passing fuses local and global temporal context to produce vocabulary-agnostic embeddings. We prove the temporal encoding is time-shift invariant and evaluate FITTER on cross-domain, cross-graph transfer over six temporal knowledge graph benchmarks of diverse domains, granularities, and time spans. FITTER consistently outperforms inductive baselines without retraining, indicating that vocabulary-agnostic structural learning is a viable foundation for inference over the heterogeneous knowledge graphs of the Semantic Web.
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。