Multi-Channel Graph Neural Network for Entity Alignment
Multi-Channel Graph Neural Network for Entity Alignment
复制标题
DOI：
10.18653/v1/p19-1140
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Yixin Cao;Zhiyuan Liu;Chengjiang Li;Zhiyuan Liu;Juan-Zi Li;Tat-Seng Chua
中科院分区：
文献类型：
--
作者：
Yixin Cao;Zhiyuan Liu;Chengjiang Li;Zhiyuan Liu;Juan-Zi Li;Tat-Seng Chua
实体比对通常存在结构异质性和种子比对有限的问题。本文提出了一种新的多通道图神经网络模型(MuGNN)来学习面向对齐的知识图(KG)嵌入，通过多个通道对两个KG进行鲁棒编码。每个通道分别通过不同的关系加权方案对KG进行编码，所述关系加权方案分别针对针对KG完成的自我注意和用于剪枝排他实体的交叉KG注意，这两种注意通过池化技术进一步组合。此外，我们还推理和传递规则知识以一致地完成两个KGS。预计MuGNN将协调两个KG的结构差异，从而更好地利用种子排列。在五个公开可用的数据集上进行的广泛实验表明，我们的性能优越(平均命中率为5%@1)。实验中使用的源代码和数据可以在https://github.com/thunlp/MuGNN上获取。
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 .