arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.00378cs.AIcs.LG
收藏

基于3D复合几何变换的知识图谱嵌入

Knowledge Graph Embedding with 3D Compound Geometric Transformations

University of Southern California(南加州大学);National University of Singapore(新加坡国立大学)

Xiou Ge, Yun-Cheng Wang, Bin Wang, C. -C. Jay Kuo

AI总结:

受CompoundE和Rotate3D启发,提出利用3D复合几何变换(平移、旋转、缩放、反射和剪切)的KGE模型族CompoundE3D,其多变体集成在四个链接预测数据集上表现优异。

摘要:

2D几何变换的级联被用于建模知识图谱(KG)中实体间的关系,产生了一种有效的KG嵌入(KGE)模型CompoundE。此外,通过利用三维空间中旋转的不可交换性,提出了一种新的KGE模型Rotate3D。受CompoundE和Rotate3D的启发,我们在本工作中利用包括平移、旋转、缩放、反射和剪切在内的3D复合几何变换,提出了一族KGE模型,命名为CompoundE3D。CompoundE3D允许有多种设计变体以匹配KG丰富的潜在特征。由于每个变体在部分关系子集上具有各自的优势,多个变体的集成可以产生更优的性能。CompoundE3D的有效性和灵活性在四个流行的链接预测数据集上得到了实验验证。

英文摘要:

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was proposed as a new KGE model, Rotate3D, by leveraging its non-commutative property. Inspired by CompoundE and Rotate3D, we leverage 3D compound geometric transformations, including translation, rotation, scaling, reflection, and shear and propose a family of KGE models, named CompoundE3D, in this work. CompoundE3D allows multiple design variants to match rich underlying characteristics of a KG. Since each variant has its own advantages on a subset of relations, an ensemble of multiple variants can yield superior performance. The effectiveness and flexibility of CompoundE3D are experimentally verified on four popular link prediction datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑