A Simple But Powerful Graph Encoder for Temporal Knowledge Graph Completion
This work addresses the computational burden in TKGC for researchers and practitioners by offering a simpler, more efficient method.
The paper tackles the problem of excessive parameters in temporal knowledge graph completion (TKGC) by proposing TARGCN, a parameter-efficient graph encoder that achieves a 46% relative improvement on the GDELT dataset and outperforms baselines with 18% fewer parameters on ICEWS05-15.
Knowledge graphs contain rich knowledge about various entities and the relational information among them, while temporal knowledge graphs (TKGs) describe and model the interactions of the entities over time. In this context, automatic temporal knowledge graph completion (TKGC) has gained great interest. Recent TKGC methods integrate advanced deep learning techniques, e.g., Transformers, and achieve superior model performance. However, this also introduces a large number of excessive parameters, which brings a heavier burden for parameter optimization. In this paper, we propose a simple but powerful graph encoder for TKGC, called TARGCN. TARGCN is parameter-efficient, and it extensively explores every entity's temporal context for learning contextualized representations. We find that instead of adopting various kinds of complex modules, it is more beneficial to efficiently capture the temporal contexts of entities. We experiment TARGCN on three benchmark datasets. Our model can achieve a more than 46% relative improvement on the GDELT dataset compared with state-of-the-art TKGC models. Meanwhile, it outperforms the strongest baseline on the ICEWS05-15 dataset with around 18% fewer parameters.