Recent embedding-based methods have achieved great successes on exploiting entity alignment from knowledge graph (KG) embeddings of multiple modals. In this paper, we study embedding-based entity alignment (EEA) from a perspective of generative models. We show that EEA is a special problem where the main objective is analogous to that in a typical generative model, based on which we theoretically prove the effectiveness of the recently developed generative adversarial network (GAN)-based EEA methods. We then reveal that their incomplete objective limits the capacity on both entity alignment and entity synthesis (i.e., generating new entities). We mitigate this problem by introducing a generative EEA (abbr., GEEA) framework with the proposed mutual variational autoencoder (M-VAE) as the generative model. M-VAE can convert an entity from one KG to another and generate new entities from random noise vectors. We demonstrate the power of GEEA with theoretical analysis and empirical experiments on both entity alignment and entity synthesis tasks.

翻译：近期基于嵌入的方法在多模态知识图谱嵌入中成功实现了实体对齐。本文从生成模型视角研究基于嵌入的实体对齐（EEA）。我们证明EEA是一个特殊问题，其主要目标与典型生成模型相似，并基于此从理论上证实了近期基于生成对抗网络（GAN）的EEA方法的有效性。随后揭示其不完整目标限制了实体对齐与实体合成（即生成新实体）的能力。我们通过提出生成式EEA（简称GEEA）框架缓解此问题，该框架采用所提出的互变分自编码器（M-VAE）作为生成模型。M-VAE可将实体从一个知识图谱转换至另一个，并从随机噪声向量生成新实体。我们通过理论分析与实体对齐及实体合成任务的实证实验证明了GEEA的能力。