针对知识图谱嵌入模型，提出基于关系域与值域的合成负例生成方法。
Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Models
- 根据关系的领域和范围生成更合理的负例
- 在标准数据集上提升10% MRR，大语料库上超150% MRR
- 适用于需高精度知识推理的场景
知识图谱嵌入模型通过低维空间表示实体与关系，在知识图谱补全与探索任务中表现优异。训练的关键之一是区分真实事实（正例）与虚假陈述（负例）。然而，知识图谱中缺失的事实未必为假，真实负例难以获取，因此合成负例成为必要。不同生成策略显著影响嵌入质量。本文改进了训练过程中尊重关系域与范围的负例生成策略，扩展其能力，并在标准基准数据集上实现10% MRR提升，在更大规模的本体驱动数据集上提升超过150% MRR。
原文摘要 · Abstract (English)
Knowledge Graph Embedding models, representing entities and edges in a low-dimensional space, have been extremely successful at solving tasks related to completing and exploring Knowledge Graphs (KGs). One of the key aspects of training most of these models is teaching to discriminate between true statements positives and false ones (negatives). However, the way in which negatives can be defined is not trivial, as facts missing from the KG are not necessarily false and a set of ground truth negatives is hardly ever given. This makes synthetic negative generation a necessity. Different generation strategies can heavily affect the quality of the embeddings, making it a primary aspect to consider. We revamp a strategy that generates corruptions during training respecting the domain and range of relations, we extend its capabilities and we show our methods bring substantial improvement (+10% MRR) for standard benchmark datasets and over +150% MRR for a larger ontology-backed dataset.
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。