Conventional representation learning algorithms for knowledge graphs (KG) map
each entity to a unique embedding vector, ignoring the rich information
contained in the neighborhood. We propose a method named StarGraph, which gives
a novel way to utilize the neighborhood information for large-scale knowledge
graphs to obtain entity representations. An incomplete two-hop neighborhood
subgraph for each target node is at first generated, then processed by a
modified self-attention network to obtain the entity representation, which is
used to replace the entity embedding in conventional methods. We achieved SOTA
performance on ogbl-wikikg2 and got competitive results on fb15k-237. The
experimental results proves that StarGraph is efficient in parameters, and the
improvement made on ogbl-wikikg2 demonstrates its great effectiveness of
representation learning on large-scale knowledge graphs. The code is now
available at https://github.com/hzli-ucas/StarGraph.

本文提出了一种名为 StarGraph 的方法，其利用在大规模知识图谱中获取实体表示的新方法 —— 生成每个目标节点的不完整的二跳邻居子图，然后通过修改的自注意力网络处理以获得实体表示，以取代传统方法中的实体嵌入。该方法在 ogbl-wikikg2 上取得了 SOTA 性能并在 fb15k-237 上具有竞争力的结果，证明了 StarGraph 在语参数上的高效，并证明了它对大规模知识图谱的表示学习的巨大效能。