Revisit and Outstrip Entity Alignment: A Perspective of Generative Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Lingbing, Chen, Zhuo, Chen, Jiaoyan, Fang, Yin, Zhang, Wen, Chen, Huajun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911783296434176
author Guo, Lingbing
Chen, Zhuo
Chen, Jiaoyan
Fang, Yin
Zhang, Wen
Chen, Huajun
author_facet Guo, Lingbing
Chen, Zhuo
Chen, Jiaoyan
Fang, Yin
Zhang, Wen
Chen, Huajun
contents Recent embedding-based methods have achieved great successes in exploiting entity alignment from knowledge graph (KG) embeddings of multiple modalities. In this paper, we study embedding-based entity alignment (EEA) from a perspective of generative models. We show that EEA shares similarities with typical generative models and prove the effectiveness of the recently developed generative adversarial network (GAN)-based EEA methods theoretically. 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 (GEEA) framework with the proposed mutual variational autoencoder (M-VAE) as the generative model. M-VAE enables entity conversion between KGs and generation of 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.
format Preprint
id arxiv_https___arxiv_org_abs_2305_14651
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Revisit and Outstrip Entity Alignment: A Perspective of Generative Models
Guo, Lingbing
Chen, Zhuo
Chen, Jiaoyan
Fang, Yin
Zhang, Wen
Chen, Huajun
Computation and Language
Information Retrieval
Machine Learning
Recent embedding-based methods have achieved great successes in exploiting entity alignment from knowledge graph (KG) embeddings of multiple modalities. In this paper, we study embedding-based entity alignment (EEA) from a perspective of generative models. We show that EEA shares similarities with typical generative models and prove the effectiveness of the recently developed generative adversarial network (GAN)-based EEA methods theoretically. 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 (GEEA) framework with the proposed mutual variational autoencoder (M-VAE) as the generative model. M-VAE enables entity conversion between KGs and generation of 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.
title Revisit and Outstrip Entity Alignment: A Perspective of Generative Models
topic Computation and Language
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2305.14651