LGAIIRMLApr 3, 2025

Knowledge Graph Completion with Mixed Geometry Tensor Factorization

arXiv:2504.02589v13 citationsh-index: 6AISTATS
Originality Incremental advance
AI Analysis

This work addresses knowledge graph completion, a key problem in AI for representing and reasoning with structured data, with incremental improvements in efficiency and performance.

The authors tackled knowledge graph completion by proposing a mixed geometry tensor factorization approach that combines Euclidean and hyperbolic components, achieving new state-of-the-art link prediction accuracy with significantly fewer parameters than previous models.

In this paper, we propose a new geometric approach for knowledge graph completion via low rank tensor approximation. We augment a pretrained and well-established Euclidean model based on a Tucker tensor decomposition with a novel hyperbolic interaction term. This correction enables more nuanced capturing of distributional properties in data better aligned with real-world knowledge graphs. By combining two geometries together, our approach improves expressivity of the resulting model achieving new state-of-the-art link prediction accuracy with a significantly lower number of parameters compared to the previous Euclidean and hyperbolic models.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes