# More is not Always Better: The Negative Impact of A-box Materialization on RDF2vec Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/2009.00318 · HTML: https://mlsanity.com/paper/2009.00318/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2020.

## Built on by (most cited first, 2 of 2)

- [Putting RDF2vec in Order](https://mlsanity.com/paper/2108.05280/) (2021)
- [pyRDF2Vec: A Python Implementation and Extension of RDF2Vec](https://mlsanity.com/paper/2205.02283/) (2022)

## Abstract (arXiv)

RDF2vec is an embedding technique for representing knowledge graph entities in a continuous vector space. In this paper, we investigate the effect of materializing implicit A-box axioms induced by subproperties, as well as symmetric and transitive properties. While it might be a reasonable assumption that such a materialization before computing embeddings might lead to better embeddings, we conduct a set of experiments on DBpedia which demonstrate that the materialization actually has a negative effect on the performance of RDF2vec. In our analysis, we argue that despite the huge body of work devoted on completing missing information in knowledge graphs, such missing implicit information is actually a signal, not a defect, and we show examples illustrating that assumption.