Deakin University
Browse

Generative adversarial network for unsupervised multi-lingual knowledge graph entity alignment

journal contribution
posted on 2024-01-04, 03:10 authored by Y Li, L Chen, C Liu, R Zhou, Jianxin Li
AbstractEntity alignment is an essential process in knowledge graph (KG) fusion, which aims to link entities representing the same real-world object in different KGs, to achieve entity expansion and graph fusion. Recently, embedding-based entity pair similarity evaluation has become mainstream in entity alignment research. However, these methods heavily rely on labelled entity pairs, which are often unavailable. Some self-supervised methods exploit features of KGs regardless of noise when generating aligned entity pairs. To resolve this issue, we propose a generative adversarial entity alignment method, which is more robust to noise data. The proposed method then exploits both attribute and structure information in the KGs and applies a BERT-based contrastive loss function to embed entities in KGs. Experimental results on several benchmark datasets demonstrate the superiority of our framework compared with most existing state-of-the-art entity alignment methods.

History

Journal

World Wide Web

Volume

26

Pagination

2265-2290

Location

Berlin, Germany

ISSN

1386-145X

eISSN

1573-1413

Language

eng

Publication classification

C1 Refereed article in a scholarly journal

Issue

5

Publisher

Springer

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC