# Knowledge Graph Embedding with Multiple Relation Projections

arXiv: https://arxiv.org/abs/1801.08641 · HTML: https://mlsanity.com/paper/1801.08641/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2018.

## Built on by (most cited first, 5 of 5)

- [Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/2103.03642/) (2021)
- [Discovering Fine-Grained Semantics in Knowledge Graph Relations](https://mlsanity.com/paper/2202.08917/) (2022)
- [Fast Knowledge Graph Completion using Graphics Processing Units](https://mlsanity.com/paper/2307.12059/) (2023)
- [Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction](https://mlsanity.com/paper/2309.11528/) (2023)
- [gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs](https://mlsanity.com/paper/2512.08274/) (2025)

## Abstract (arXiv)

Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data. One of the most effective methods in representing knowledge graphs is to embed symbolic relations and entities into continuous spaces, where relations are approximately linear translation between projected images of entities in the relation space. However, state-of-the-art relation projection methods such as TransR, TransD or TransSparse do not model the correlation between relations, and thus are not scalable to complex knowledge graphs with thousands of relations, both in computational demand and in statistical robustness. To this end we introduce TransF, a novel translation-based method which mitigates the burden of relation projection by explicitly modeling the basis subspaces of projection matrices. As a result, TransF is far more light weight than the existing projection methods, and is robust when facing a high number of relations. Experimental results on the canonical link prediction task show that our proposed model outperforms competing rivals by a large margin and achieves state-of-the-art performance. Especially, TransF improves by 9%/5% in the head/tail entity prediction task for N-to-1/1-to-N relations over the best performing translation-based method.