SRREN: self-aware and relation-aware recurrent evolution network for temporal knowledge graph reasoning
Document Type
Article
Publication Date
12-1-2026
Abstract
Predicting incomplete temporal knowledge graphs (TKGs) presents a significant challenge, as it requires effectively capturing both the structural dependencies between concurrent facts and the dynamic evolution of relationships over time. To address this, we propose the Self-aware and Relation-aware Recurrent Evolution Network (SRREN), a novel recursive algorithm for dynamic representation learning in TKGs. SRREN integrates an evolution unit and a score calculation unit, where the former combines two synergistic modules: (1) The self-aware mechanism employs dual-channel attention with global averaging and local median scaling within fixed time windows, leveraging GRU-based gating to balance long-term trends and outlier-resistant local features. (2) The relation-aware mechanism introduces a GRU-enhanced memory bank and adaptive relation weighting, coupled with GCN propagation to model cross-subgraph relationship evolution. The score unit further incorporates GCN-based decoders to enhance entity-relation interaction modeling. Crucially, SRREN unifies static entity attributes with dynamic relational features through recursive temporal gating, enabling context-sensitive adaptation. Experiments on six benchmark (ICEWS18, GDELT, etc.) show that SRREN can improve the accuracy of predicting future facts, and its performance is better than most other current models.
Keywords
Evolutional representation learning, Graph convolution network, Temporal knowledge graph
Publication Title
Knowledge and Information Systems
ISSN
0219-1377
DOI
10.1007/s10115-026-02713-5
Recommended Citation
Zhao, Laibin; Ratnavelu, Kuru; and ALDharhani, Ghassan Saleh, "SRREN: self-aware and relation-aware recurrent evolution network for temporal knowledge graph reasoning" (2026). Research Publications (2026 to 2030). 413.
https://knova.um.edu.my/research_publications_2026_2030/413
Volume
68
Issue
1