RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion
This work addresses the need for better interpretability and modeling of evolving relations in TKGs, which is important for applications like disease progression and political analysis, though it is incremental in advancing existing temporal modeling techniques.
The paper tackled the problem of modeling temporal relation patterns in Temporal Knowledge Graphs (TKGs) by proposing RotateQVS, a method that represents temporal entities as rotations in quaternion vector space and relations as complex vectors, which improved link prediction performance on four benchmarks.
Temporal factors are tied to the growth of facts in realistic applications, such as the progress of diseases and the development of political situation, therefore, research on Temporal Knowledge Graph (TKG) attracks much attention. In TKG, relation patterns inherent with temporality are required to be studied for representation learning and reasoning across temporal facts. However, existing methods can hardly model temporal relation patterns, nor can capture the intrinsic connections between relations when evolving over time, lacking of interpretability. In this paper, we propose a novel temporal modeling method which represents temporal entities as Rotations in Quaternion Vector Space (RotateQVS) and relations as complex vectors in Hamilton's quaternion space. We demonstrate our method can model key patterns of relations in TKG, such as symmetry, asymmetry, inverse, and can further capture time-evolved relations by theory. Empirically, we show that our method can boost the performance of link prediction tasks over four temporal knowledge graph benchmarks.