Abstract
Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task. However, we found that inherent heterogeneity among factor tensors in tensor decomposition significantly hinders the tensor fusion process and further limits the performance of link prediction. To overcome this limitation, we introduce a novel method that maps factor tensors onto a unified smooth Lie group manifold to make the distribution of factor tensors approximating homogeneous in tensor decomposition. We provide the theoretical proof of our motivation that homogeneous tensors are more effective than heterogeneous tensors in tensor fusion and approximating the target for tensor decomposition based TKGE methods. The proposed method can be directly integrated into existing tensor decomposition based TKGE methods without introducing extra parameters. Extensive experiments demonstrate the effectiveness of our method in mitigating the heterogeneity and in enhancing the tensor decomposition based TKGE models.
Abstract (translated)
近年来，研究表明在 Temporal Knowledge Graph Embedding（TKGE）任务中，张量分解方法具有显著的有效性。然而，我们发现，在张量分解中，因素张量的固有异质性严重阻碍了张量融合过程，并进一步限制了链路预测的性能。为了克服这一局限，我们引入了一种新的方法，将因素张量映射到统一的平滑李群流形上，使因素张量的分布在张量分解中近似均匀。我们提供了基于 TKGE 方法的动机，即均匀张量比异质张量在张量融合和基于 TKGE 的目标建模中更有效。所提出的方法可以直接集成到现有的基于 TKGE 的张量分解方法中，而无需引入额外的参数。大量实验证明，我们的方法在减轻异质性和增强基于 TKGE 的张量分解模型方面具有有效性。
URL
https://arxiv.org/abs/2404.09155
