# Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings

arXiv: https://arxiv.org/abs/2606.03365 · HTML: https://mlsanity.com/paper/2606.03365/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [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 Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning](https://mlsanity.com/paper/1711.05851/) (2017)
- [A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network](https://mlsanity.com/paper/1712.02121/) (2017)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs](https://mlsanity.com/paper/2003.07743/) (2020)
- [CoDEx: A Comprehensive Knowledge Graph Completion Benchmark](https://mlsanity.com/paper/2009.07810/) (2020)
- [Analogical Inference for Multi-Relational Embeddings](https://mlsanity.com/paper/1705.02426/) (2017)
- [Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning](https://mlsanity.com/paper/1903.08948/) (2019)
- [Type-Constrained Representation Learning in Knowledge Graphs](https://mlsanity.com/paper/1508.02593/) (2015)
- [On Model Stability as a Function of Random Seed](https://mlsanity.com/paper/1909.10447/) (2019)
- [Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery](https://mlsanity.com/paper/2105.10488/) (2021)
- [The Effects of Randomness on the Stability of Node Embeddings](https://mlsanity.com/paper/2005.10039/) (2020)
- [Knowledge Graphs for the Life Sciences: Recent Developments, Challenges and Opportunities](https://mlsanity.com/paper/2309.17255/) (2023)
- [Geometric Relational Embeddings: A Survey](https://mlsanity.com/paper/2304.11949/) (2023)
- [Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction](https://mlsanity.com/paper/2408.08226/) (2024)
- [Discovering alignment relations with Graph Convolutional Networks: a biomedical case study](https://mlsanity.com/paper/2011.06023/) (2020)
- [Do Similar Entities have Similar Embeddings?](https://mlsanity.com/paper/2312.10370/) (2023)

## Built on by (most cited first, 1 of 1)

- [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)

Embedding models (KGEMs) constitute the main link prediction approach to complete knowledge graphs. Standard evaluation protocols emphasize rank-based metrics such as MRR or Hits@K, but usually overlook the influence of random seeds on result stability. Moreover, these metrics conceal potential instabilities in individual predictions and in the organization of embedding spaces. In this work, we conduct a systematic stability analysis of multiple KGEMs across several datasets. We find that high-performance models actually produce divergent predictions at the triple level and highly variable embedding spaces. By isolating stochastic factors (i.e., initialization, triple ordering, negative sampling, dropout, hardware), we show that each independently induces instability of comparable magnitude. Furthermore, for a given model, hyperparameter configurations with better MRR are not guaranteed to be more stable. Moreover, voting, albeit a known remediation mechanism, only provides a limited enhancement of stability. These findings highlight critical limitations of current benchmarking protocols, and raise concerns about the reliability of KGEMs for knowledge graph completion.