摘要

实体对齐通常面临结构异构和有限种子对齐的问题。在本文中，我们提出了一种新的多通道图神经网络模型（MuGNN），通过多通道鲁棒编码两个KG来学习面向对齐的知识图嵌入。每个通道通过不同的关系加权方案对KG进行编码，分别涉及KG完成的自注意力和交叉KG注意力，用于修剪排他实体，这两种方案通过池技术进一步组合。此外，我们还推断和传递规则知识，以一致地完成两个KG。MuGNN有望调和两个KG的结构差异，从而更好地利用种子比对。在五个公开数据集上进行的大量实验表明，我们的性能优越（5%Hits@1平均上升）。实验中使用的源代码和数据可访问[链接](https://github.com/thunlp/MuGNN)。
Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https://github.com/thunlp/MuGNN.
知识图以有向图的形式存储世界知识，其中节点表示实体，边表示它们之间的关系。自提出以来，构建了许多KG（例如YAGO（Rebele等人，2016））以提供不同应用程序和语言的结构知识。这些知识库通常包含互补的内容，吸引研究人员将其集成到一个统一的知识库中，这将有利于许多知识驱动的任务，例如信息提取（Cao等人，2018a）和推荐（Wang等人，2018a）。由于不同的KG具有不同的表面形式，因此对齐不同的KG是非常重要的，这使得基于符号的方法（Suchanek等人，2011）并非如此。
Knowledge Graphs (KGs) store the world knowledge in the form of directed graphs, where nodes denote entities and edges are their relations. Since it was proposed, many KGs are constructed (e.g., YAGO (Rebele et al., 2016)) to provide structural knowledge for different applications and languages. These KGs usually contain complementary contents, attracting researchers to integrate them into a unified KG, which shall benefit many knowledge driven tasks, such as information extraction (Cao et al., 2018a) and recommendation (Wang et al., 2018a). It is non-trivial to align different KGs due to their distinct surface forms, which makes the symbolic based methods (Suchanek et al., 2011) not