DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach

TL;DR

DECRL is a novel deep evolutionary clustering method for temporal knowledge graphs that captures high-order correlations and maintains temporal cluster smoothness, achieving state-of-the-art performance on real datasets.

Contribution

The paper introduces a deep evolutionary clustering module, a cluster-aware alignment mechanism, and an implicit correlation encoder for TKGs, advancing temporal representation learning.

Findings

Outperforms baselines with an average of 9.53% in MRR

Achieves 12.98% improvement in Hits@1

Demonstrates effectiveness on seven real-world datasets

Abstract

Temporal Knowledge Graph (TKG) representation learning aims to map temporal evolving entities and relations to embedded representations in a continuous low-dimensional vector space. However, existing approaches cannot capture the temporal evolution of high-order correlations in TKGs. To this end, we propose a Deep Evolutionary Clustering jointed temporal knowledge graph Representation Learning approach (DECRL). Specifically, a deep evolutionary clustering module is proposed to capture the temporal evolution of high-order correlations among entities. Furthermore, a cluster-aware unsupervised alignment mechanism is introduced to ensure the precise one-to-one alignment of soft overlapping clusters across timestamps, thereby maintaining the temporal smoothness of clusters. In addition, an implicit correlation encoder is introduced to capture latent correlations between any pair of clusters under the guidance of a global graph. Extensive experiments on seven real-world datasets demonstrate that DECRL achieves the state-of-the-art performances, outperforming the best baseline by an average of 9.53%, 12.98%, 10.42%, and 14.68% in MRR, Hits@1, Hits@3, and Hits@10, respectively.