# Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/2104.05003 · HTML: https://mlsanity.com/paper/2104.05003/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 11 Apr 2021.

## Builds on (most cited first, 12 of 12)

- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Quaternion Knowledge Graph Embeddings](https://mlsanity.com/paper/1904.10281/) (2019)
- [Canonical Tensor Decomposition for Knowledge Base Completion](https://mlsanity.com/paper/1806.07297/) (2018)
- [TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation](https://mlsanity.com/paper/2010.01029/) (2020)
- [Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study](https://mlsanity.com/paper/2003.08001/) (2020)
- [Knowledge Graph Embeddings in Geometric Algebras](https://mlsanity.com/paper/2010.00989/) (2020)
- [Linear Ensembles of Word Embedding Models](https://mlsanity.com/paper/1704.01419/) (2017)
- [Toward Understanding The Effect Of Loss function On Then Performance Of Knowledge Graph Embedding](https://mlsanity.com/paper/1909.00519/) (2019)

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

- [Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models](https://mlsanity.com/paper/2302.06229/) (2023)
- [Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction](https://mlsanity.com/paper/2408.08226/) (2024)
- [Adaptive Stochastic Weight Averaging](https://mlsanity.com/paper/2406.19092/) (2024)
- [SnapE -- Training Snapshot Ensembles of Link Prediction Models](https://mlsanity.com/paper/2408.02707/) (2024)
- [Knowledge Graph Embedding with 3D Compound Geometric Transformations](https://mlsanity.com/paper/2304.00378/) (2023)
- [SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs](https://mlsanity.com/paper/2507.13001/) (2025)
- [Parameter Averaging in Link Prediction](https://mlsanity.com/paper/2510.25361/) (2025)
- [Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models](https://mlsanity.com/paper/2609.02638/) (2026)

## Abstract (arXiv)

Among the top approaches of recent years, link prediction using knowledge graph embedding (KGE) models has gained significant attention for knowledge graph completion. Various embedding models have been proposed so far, among which, some recent KGE models obtain state-of-the-art performance on link prediction tasks by using embeddings with a high dimension (e.g. 1000) which accelerate the costs of training and evaluation considering the large scale of KGs. In this paper, we propose a simple but effective performance boosting strategy for KGE models by using multiple low dimensions in different repetition rounds of the same model. For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same. We show that our approach enables different models to better cope with their expressiveness issues on modeling various graph patterns such as symmetric, 1-n, n-1 and n-n. In order to justify our findings, we conduct experiments on various KGE models. Experimental results on standard benchmark datasets, namely FB15K, FB15K-237 and WN18RR, show that multiple low-dimensional models of the same kind outperform the corresponding single high-dimensional models on link prediction in a certain range and have advantages in training efficiency by using parallel training while the overall numbers of adjustable parameters are same.