# Improved Knowledge Graph Embedding using Background Taxonomic Information

arXiv: https://arxiv.org/abs/1812.03235 · HTML: https://mlsanity.com/paper/1812.03235/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2018.

## Built on by (most cited first, 8 of 8)

- [Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey](https://mlsanity.com/paper/2302.07200/) (2023)
- [Knowledge Hypergraph Embedding Meets Relational Algebra](https://mlsanity.com/paper/2102.09557/) (2021)
- [MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language](https://mlsanity.com/paper/2409.12257/) (2024)
- [Learning to Substitute Ingredients in Recipes](https://mlsanity.com/paper/2302.07960/) (2023)
- [Knowledge Enhanced Graph Neural Networks for Graph Completion](https://mlsanity.com/paper/2303.15487/) (2023)
- [TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation](https://mlsanity.com/paper/2306.14580/) (2023)
- [Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules](https://mlsanity.com/paper/2301.02781/) (2023)
- [Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs](https://mlsanity.com/paper/2106.14052/) (2021)

## Abstract (arXiv)

Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is background taxonomic information (in terms of subclasses and subproperties) that should also be taken into account. We show that existing fully expressive (a.k.a. universal) models cannot provably respect subclass and subproperty information. We show that minimal modifications to an existing knowledge graph completion method enables injection of taxonomic information. Moreover, we prove that our model is fully expressive, assuming a lower-bound on the size of the embeddings. Experimental results on public knowledge graphs show that despite its simplicity our approach is surprisingly effective.