# Irreflexive and Hierarchical Relations as Translations

arXiv: https://arxiv.org/abs/1304.7158 · HTML: https://mlsanity.com/paper/1304.7158/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2013.

## Built on by (most cited first, 4 of 4)

- [Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces](https://mlsanity.com/paper/2211.03536/) (2022)
- [Ultrahyperbolic Knowledge Graph Embeddings](https://mlsanity.com/paper/2206.00449/) (2022)
- [Searching to Sparsify Tensor Decomposition for N-ary Relational Data](https://mlsanity.com/paper/2104.10625/) (2021)
- [Knowledge Graph Completion Method Combined With Adaptive Enhanced Semantic Information](https://mlsanity.com/paper/2302.02116/) (2023)

## Abstract (arXiv)

We consider the problem of embedding entities and relations of knowledge bases in low-dimensional vector spaces. Unlike most existing approaches, which are primarily efficient for modeling equivalence relations, our approach is designed to explicitly model irreflexive relations, such as hierarchies, by interpreting them as translations operating on the low-dimensional embeddings of the entities. Preliminary experiments show that, despite its simplicity and a smaller number of parameters than previous approaches, our approach achieves state-of-the-art performance according to standard evaluation protocols on data from WordNet and Freebase.