Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings.

翻译：基于图神经网络的方法在各种知识图谱任务中展现了显著性能。然而，现有方法大多依赖于在训练期间观察所有实体，这在现实知识图谱中面临新实体频繁出现的挑战。为解决这一局限，我们提出了分散注意力网络（DAN）。DAN利用邻居上下文作为查询向量对实体的邻居进行评分，从而仅将实体语义分布在其邻居嵌入之间。为有效训练DAN，我们引入了自蒸馏技术，该技术引导网络生成期望的表示。理论分析验证了我们方法的有效性。我们实现了端到端框架并进行了大量实验评估，在传统实体对齐和实体预测任务中展现了竞争性能。此外，我们的方法在开放世界环境下显著优于现有方法。