arrow
Return

MultiJAF: Multi-modal joint entity alignment framework for multi-modal knowledge graph

delete2022-08-01
delete15
PRE
AI
B
Bo Cheng
J
Jia Zhu *
M
Meimei Guo
DOI:10.1016/j.neucom.2022.05.058delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Entity Alignment (EA) is a crucial task in knowledge fusion, which aims to link entities with the same real-world identity from different Knowledge Graphs (KGs). Existing methods have achieved satisfactory performance, however, they mainly focus on single modal KG, which is difficult to be effectively applied to multi-modal scenes. In this paper, we propose a Multi-modal Joint entity Alignment Framework (MultijAF), which can effectively utilize the knowledge of various modalities. Concretely, we first learn the embeddings of different modalities, i.e., structure, attribute and image modalities. Next, we adopt an attention-based multi-modal fusion network to integrate these embeddings and use obtained joint embeddings to compute a joint embedding-based similarity matrix S-J. Moreover, we design a Numerical Process Module (NPM) to infer a similarity matrix S-N according to the numerical information of entities. In the end, we utilize a simple late fusion method to ensemble two similarity matrices for the final alignment. In addition, to reduce the cost of labeling data, we propose a novel NPM-based unsupervised multi-modal EA method. Experimental results on two real-world datasets demonstrate the effectiveness of our proposed MultijAF. (C) 2022 Elsevier B.V. All rights reserved.
Keywords:
Entity alignment
Multi-modal fusion
Multi-modal knowledge graph

Journal

Neurocomputing cover
Neurocomputing
IF:
6.5
Papers:
2.5W
Citations:
6.5W

Organization

S
south china normal university
Scholars:
2.0W
Papers: 1.3W
Citations: 13
Z
Zhejiang Normal University
Scholars:
1.3W
Papers: 8.4K
Citations: 1.2W
Cited Papers

Cited Papers

Exploiting hierarchical visual features for visual question answering
err2019-07-01
err9
PREAI
errHong, Jongkwang; Fu, Jianlong; Uh, Youngjung; Mei, Tao; Byun, Hyeran
errShare
errSave
Ion microprobe analyses of oxygen three‐isotope ratios of chondrules from the Sayh al Uhaymir 290 CH chondrite using a multiple‐hole disk
err2011-05-31
err0
errOAAI
errDaisuke NAKASHIMA; Takayuki USHIKUBO; Rudraswami N. GOWDA; Noriko T. KITA; John W. VALLEY; Keisuke NAGAO
errShare
errSave
Knowledge graph based natural language generation with adapted pointer-generator networks
err2020-03-01
err22
PREAI
errLi, Weidong; Peng, Rong; Wang, Yaqian; Yan, Zhihuan
errShare
errSave
Interactions Guided Generative Adversarial Network for unsupervised image captioning
err2020-12-01
err23
PREAI
errCao, Shan; An, Gaoyun; Zheng, Zhenxing; Ruan, Qiuqi
errShare
errSave
Explore Modeling Relation Information and Direction Information in KBQA
err2022-01-01
err7
PREAI
errWang, Xu; Zhao, Shuai; Cheng, Bo; Yin, Yuwei; Yang, Hao
errShare
errSave
Knowledge-based question answering by tree-to-sequence learning
err2020-01-01
err50
PREAI
errZhu, Shuguang; Cheng, Xiang; Su, Sen
errShare
errSave
TransMKR: Translation-based knowledge graph enhanced multi-task point-of-interest recommendation
err2022-02-01
err29
PREAI
errHu, Bojing; Ye, Yaqin; Zhong, Yingqiang; Pan, Jiao; Hu, Maosheng
errShare
errSave
researcher View more