LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding

For knowledge graphs, knowledge graph embedding (KGE) models learn to project the symbolic entities and relations into a low-dimensional continuous vector space based on the observed triplets. However, existing KGE models can not 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 uses an iterative aggregation strategy to integrate the context information in multi-hop into the entity/relation embeddings, also explicitly models the graph context without introducing extra trainable parameters other than embeddings. Moreover, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework.