# Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation

arXiv: https://arxiv.org/abs/2011.05301 · HTML: https://mlsanity.com/paper/2011.05301/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers](https://mlsanity.com/paper/2305.18256/) (2023)
- [Knowledge Graph Reasoning over Entities and Numerical Values](https://mlsanity.com/paper/2306.01399/) (2023)
- [Augmenting Knowledge Graphs for Better Link Prediction](https://mlsanity.com/paper/2203.13965/) (2022)
- [AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2301.03049/) (2023)
- [Incomplete Graph Learning: A Comprehensive Survey](https://mlsanity.com/paper/2502.12412/) (2025)
- [Propagation on Multi-relational Graphs for Node Regression](https://mlsanity.com/paper/2110.08185/) (2021)
- [Bridging the Semantic-Numerical Gap: A Numerical Reasoning Method of Cross-modal Knowledge Graph for Material Property Prediction](https://mlsanity.com/paper/2312.09744/) (2023)
- [Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs](https://mlsanity.com/paper/2608.26729/) (2026)

## Abstract (arXiv)

The existing literature on knowledge graph completion mostly focuses on the link prediction task. However, knowledge graphs have an additional incompleteness problem: their nodes possess numerical attributes, whose values are often missing. Our approach, denoted as MrAP, imputes the values of missing attributes by propagating information across the multi-relational structure of a knowledge graph. It employs regression functions for predicting one node attribute from another depending on the relationship between the nodes and the type of the attributes. The propagation mechanism operates iteratively in a message passing scheme that collects the predictions at every iteration and updates the value of the node attributes. Experiments over two benchmark datasets show the effectiveness of our approach.