What question did this study set out to answer?

To enhance temporal knowledge graph reasoning by addressing data incompleteness and improving predictive accuracy through semantic-structural fusion.

February 12, 2026Open Access

Temporal Knowledge Graph Reasoning: Completion with Semantic–Structural Fusion and Forecasting with an Interpretable Dual Decoder

Puntos clave

To enhance temporal knowledge graph reasoning by addressing data incompleteness and improving predictive accuracy through semantic-structural fusion.
Developed SiSe for completion, integrating semantic and structural embeddings using cross-attention.
Introduced DL-CompGCN for prediction that utilizes time-aware graph convolutional encoder and dual-decoder framework.
Performed experiments on ICEWS14, ICEWS05-15, and GDELT datasets to evaluate completion and prediction performance.
SiSe improved Mean Reciprocal Rank (MRR) by 1.2, 1.4, and 0.8 percentage points on respective datasets.
DL-CompGCN achieved state-of-the-art performance on ICEWS14, ICEWS05-15, and ICEWS18.
Both models outperformed baseline methods, demonstrating effective handling of symmetric temporal relationships.

Resumen

Temporal knowledge graphs (TKGs) effectively represent dynamic facts by incorporating a temporal dimension, yet they frequently encounter data incompleteness issues that constrain downstream applications. Concurrently, TKG prediction tasks, which enable reasoning about future events, have garnered significant attention. Existing TKG completion methods often neglect semantic information, underexploit event information from subsequent timestamps, and fail to leverage the structural symmetries inherent in temporal data. To address these limitations, this paper proposes a synergistic approach comprising two models: SiSe for completion and DL-CompGCN for prediction. SiSe integrates semantic and structural embeddings by employing entity text descriptions as semantic signals, utilizing symmetric cross-attention for bidirectional feature fusion and leveraging bidirectional gated recurrent units to capture symmetric temporal influences from both past and future events. On ICEWS14, ICEWS05-15, and GDELT completion datasets, the MRR improves by 1.2, 1.4, and 0.8 percentage points, respectively. DL-CompGCN addresses the accuracy–interpretability trade-off in prediction tasks through a time-aware graph convolutional encoder and a dual-decoder framework that combines bilinear scoring with first-order logical rules to generate interpretable paths while preserving the symmetric properties of temporal relations. It achieves state-of-the-art performance on ICEWS14, ICEWS05-15, and ICEWS18 prediction datasets. The proposed models explicitly incorporate symmetric principles in their architectural design; SiSe employs symmetric bidirectional temporal modeling, while DL-CompGCN maintains symmetry in its graph propagation and rule inference mechanisms. The experimental results demonstrate that both models significantly outperform baseline methods, offering a comprehensive solution for temporal knowledge graph reasoning that respects and exploits the symmetric structures inherent in temporal data.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo