融合双几何结构，用更少参数实现知识图谱补全新纪录
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
- 结合欧式与双曲几何，通过张量分解建模关系
- 在多个数据集上超越现有模型，参数量显著减少
- 适合对高效高精度知识图谱建模有需求的研究者
本文提出一种基于低秩张量逼近的新几何方法，用于知识图谱补全。在基于Tucker张量分解的预训练欧式模型基础上，引入新颖的双曲交互项，更精细地捕捉数据分布特性，使其更契合真实世界知识图谱的结构。通过融合两种几何空间，提升模型表达能力，在保持极低参数量的同时，实现新的链接预测性能纪录，优于以往的纯欧式与双曲模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。