Knowledge graph embedding (KGE) models learn to project symbolic entities and relations into a continuous vector space based on the observed triplets. However, existing KGE models cannot make a proper trade-off between the graph context and the model complexity, which makes them still far from satisfactory. In this paper, we propose a lightweight framework named LightCAKE for context-aware KGE. LightCAKE explicitly models the graph context without introducing redundant trainable parameters, and uses an iterative aggregation strategy to integrate the context information into the entity/relation embeddings. As a generic framework, it can be used with many simple KGE models to achieve excellent results. Finally, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework.
@article{arxiv.2102.10826,
title = {LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding},
author = {Zhiyuan Ning and Ziyue Qiao and Hao Dong and Yi Du and Yuanchun Zhou},
journal= {arXiv preprint arXiv:2102.10826},
year = {2021}
}