Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space
This addresses memory and training time consumption problems for researchers and practitioners scaling up knowledge graphs in NLP tasks, though it is incremental as it builds on existing KGE models.
The paper tackles the computational load issues in Knowledge Graph Embedding (KGE) models by proposing a parameter-sharing method using conjugate parameters for complex numbers, achieving 2x memory efficiency in relation embedding with comparable performance to state-of-the-art non-conjugate models and faster or comparable training time.
A Knowledge Graph (KG) is the directed graphical representation of entities and relations in the real world. KG can be applied in diverse Natural Language Processing (NLP) tasks where knowledge is required. The need to scale up and complete KG automatically yields Knowledge Graph Embedding (KGE), a shallow machine learning model that is suffering from memory and training time consumption issues. To mitigate the computational load, we propose a parameter-sharing method, i.e., using conjugate parameters for complex numbers employed in KGE models. Our method improves memory efficiency by 2x in relation embedding while achieving comparable performance to the state-of-the-art non-conjugate models, with faster, or at least comparable, training time. We demonstrated the generalizability of our method on two best-performing KGE models $5^{\bigstar}\mathrm{E}$ and $\mathrm{ComplEx}$ on five benchmark datasets.