Pattern Over-Generalization of Knowledge Graph Embedding

ACL ARR 2026 January Submission8143 Authors

Keywords: Knowledge Graph Embedding, Link Prediction, Inference Pattern

Abstract: Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in knowledge graphs (KGs) by projecting entities and relations into a low-dimensional vector space. It is crucial for KGE models to effectively capture inference patterns (patterns) inherent in KGs, such as symmetry/antisymmetry, inversion and composition. Although recent KGE models exhibit strong capabilities in modeling such diverse patterns, they suffer from inherent limitations stemming from pattern over-generalization, where embeddings learned from only a single pattern instance inevitably generalize that pattern to all related instances, i.e., generalize the pattern universally. To address this issue, we propose POGE (Pattern Over-Generalization Addressed Embedding), a simple but effective method that utilizes linear transformations and compound operations for relation representation. Our theoretical analysis demonstrates that a simple linear transformation allows a pattern to become progressively universal as more triples are observed in the pattern. Furthermore, after observing $d+1$ linearly independent entities ($d+1$ denotes the dimension of entity), the linear transformation guarantees universal generalization of the pattern across all related instances. Experimental results on three standard benchmark datasets show that POGE outperforms existing state-of-the-art KGE models in link prediction. Moreover, our empirical results indicate that POGE effectively addresses the negative impact of over-generalization.

Paper Type: Long

Research Area: Information Extraction and Retrieval

Research Area Keywords: knowledge graph completion, knowledge graph embedding

Contribution Types: Model analysis & interpretability, NLP engineering experiment

Languages Studied: English

Submission Number: 8143