Abstract
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.
Abstract (translated)
URL
https://arxiv.org/abs/2102.10826