# SnapE -- Training Snapshot Ensembles of Link Prediction Models

arXiv: https://arxiv.org/abs/2408.02707 · HTML: https://mlsanity.com/paper/2408.02707/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Builds on (most cited first, 18 of 18)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [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)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings](https://mlsanity.com/paper/2007.14175/) (2020)
- [The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares](https://mlsanity.com/paper/1904.12838/) (2019)
- [Open-World Knowledge Graph Completion](https://mlsanity.com/paper/1711.03438/) (2017)
- [Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations](https://mlsanity.com/paper/2110.02834/) (2021)
- [Knowledge Graphs on the Web -- an Overview](https://mlsanity.com/paper/2003.00719/) (2020)
- [Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models](https://mlsanity.com/paper/2302.06229/) (2023)
- [DyLink2Vec: Effective Feature Representation for Link Prediction in Dynamic Networks](https://mlsanity.com/paper/1804.05755/) (2018)
- [Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings](https://mlsanity.com/paper/2104.05003/) (2021)
- [Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInE](https://mlsanity.com/paper/2306.03659/) (2023)

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

- [DyTTP: Trajectory Prediction with Normalization-Free Transformers](https://mlsanity.com/paper/2504.05356/) (2025)
- [Improving Knowledge Graph Embeddings through Contrastive Learning with Negative Statements](https://mlsanity.com/paper/2510.11868/) (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)

Snapshot ensembles have been widely used in various fields of prediction. They allow for training an ensemble of prediction models at the cost of training a single one. They are known to yield more robust predictions by creating a set of diverse base models. In this paper, we introduce an approach to transfer the idea of snapshot ensembles to link prediction models in knowledge graphs. Moreover, since link prediction in knowledge graphs is a setup without explicit negative examples, we propose a novel training loop that iteratively creates negative examples using previous snapshot models. An evaluation with four base models across four datasets shows that this approach constantly outperforms the single model approach, while keeping the training time constant.