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

Abstract

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.

Paper accepted at ESWC 2026 (https://2026.eswc-conferences.org)

References in corpus (9)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Knowledge Graphs
• RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• The Effects of Randomness on the Stability of Node Embeddings
• Knowledge Graphs for the Life Sciences: Recent Developments, Challenges and Opportunities
• Discovering alignment relations with Graph Convolutional Networks: a biomedical case study
• Geometric Relational Embeddings: A Survey