Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs

2026-08-27

AI Summary

提出了一种神经回归模型LitEm，结合知识图谱嵌入模型预测数值属性，并通过共训练框架提高链接预测性能。

Abstract

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.

Problem

• knowledge graph
• numerical attributes
• embedding models
• prediction

Innovation

• Neural Regression
• Knowledge Graph Embeddings
• Numerical Attribute Prediction
• Co-training Framework