论文标题
Stargraph：基于不完整的两跳子图的知识表示学习
StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph
论文作者
论文摘要
传统表示知识图（KG）的学习算法将每个实体映射到独特的嵌入向量，而忽略了社区中包含的丰富信息。我们提出了一种名为Stargraph的方法，该方法提供了一种新颖的方法，可以利用大规模知识图来获取实体表示形式。首先生成每个目标节点的不完整的两个跳跃邻域子图，然后由修改的自我发项网络处理以获取实体表示，该表示该表示该表示的代表替代了传统方法中的实体嵌入。我们在OGBL Wikikg2上取得了SOTA的性能，并在FB15K-237上取得了竞争成绩。实验结果证明了Stargraph在参数方面有效，并且OGBL-Wikikg2的改进证明了其在大规模知识图上的表示有效性。该代码现在可在\ url {https://github.com/hzli-ucas/stargraph}上获得。
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 \url{https://github.com/hzli-ucas/StarGraph}.
