发表机构
Heinz Nixdorf Institute, Paderborn University（帕德博恩大学海因茨·尼克斯多夫研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出神经回归模型LitEm及协同训练框架，使直推式知识图谱嵌入模型可预测数值属性，在多数据集上取得优异性，还提升了双线性模型的链接预测性能。
AI 中文摘要
近年来，直推式知识图谱嵌入模型已被应用于链接预测、查询回答等任务。尽管知识图谱通常包含丰富的数值属性，但大多数嵌入模型忽略了这些属性，限制了其表示具有多样信息的现实世界知识图谱的能力。本研究中，我们提出了一种神经回归模型LitEm，该模型可使直推式知识图谱嵌入模型预测知识图谱内的数值属性。实验结果表明，LitEm在FB15K-237、YAGO15K、DB15K和Mutagenesis的大多数属性上取得了最优或次优结果。此外，我们提出了一种协同训练框架，该框架将最先进的直推式知识图谱嵌入模型与LitEm联合训练，主要针对双线性模型提升了链接预测性能，同时使这些模型能够预测数值属性。另外，字面感知评估表明，协同训练有助于模型以“字面感知”的方式编码和利用属性信息，说明观察到的性能提升并非仅源于额外参数。我们在该httpsURL公开了代码实现。
英文摘要
In recent years, transductive knowledge graph embedding models have been applied to tasks such as link prediction and query answering. Although knowledge graphs often contain rich numerical attributes, most embedding models neglect them, limiting their ability to represent real-world knowledge graphs with diverse information. In this work, we propose a neural regression model (LitEm) that enables transductive knowledge graph embedding models to predict numerical attributes within knowledge graphs. Experimental results demonstrate that LitEm achieves the best or second-best results on most attributes across FB15K-237, YAGO15K, DB15K, and Mutagenesis. Furthermore, we propose a co-training framework that jointly trains state-of-the-art transductive knowledge graph embedding models with LitEm, which improves link prediction performance mainly for bilinear models and simultaneously enables them to predict numerical attributes. In addition, the literal-awareness evaluation demonstrates that co-training helps models to encode and exploit attribute information in a "literal-aware'' manner, suggesting that the observed gains are not merely due to additional parameters. We publicly release our implementation at https://github.com/dice-group/dice-embeddings.
