Home > Research > Publications & Outputs > Relation-Aware Entity Alignment for Heterogeneo...

Electronic data

  • ijcai2019_4147_submission

    Accepted author manuscript, 750 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published

Standard

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs. / Wu, Yuting; Liu, Xiao; Feng, Yansong; Wang, Zheng; Yan, Rui; Zhao, Dongyan.

The 28th International Joint Conference on Artificial Intelligence (IJCAI). IJCAI, 2019. p. 5278-5284.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Harvard

Wu, Y, Liu, X, Feng, Y, Wang, Z, Yan, R & Zhao, D 2019, Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs. in The 28th International Joint Conference on Artificial Intelligence (IJCAI). IJCAI, pp. 5278-5284. https://doi.org/10.24963/ijcai.2019/733

APA

Wu, Y., Liu, X., Feng, Y., Wang, Z., Yan, R., & Zhao, D. (2019). Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs. In The 28th International Joint Conference on Artificial Intelligence (IJCAI) (pp. 5278-5284). IJCAI. https://doi.org/10.24963/ijcai.2019/733

Vancouver

Wu Y, Liu X, Feng Y, Wang Z, Yan R, Zhao D. Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs. In The 28th International Joint Conference on Artificial Intelligence (IJCAI). IJCAI. 2019. p. 5278-5284 https://doi.org/10.24963/ijcai.2019/733

Author

Wu, Yuting ; Liu, Xiao ; Feng, Yansong ; Wang, Zheng ; Yan, Rui ; Zhao, Dongyan. / Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs. The 28th International Joint Conference on Artificial Intelligence (IJCAI). IJCAI, 2019. pp. 5278-5284

Bibtex

@inproceedings{229934ecbd564bf3990e8dffb2addda7,
title = "Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs",
abstract = "Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.",
author = "Yuting Wu and Xiao Liu and Yansong Feng and Zheng Wang and Rui Yan and Dongyan Zhao",
year = "2019",
month = jul
day = "31",
doi = "10.24963/ijcai.2019/733",
language = "English",
pages = "5278--5284",
booktitle = "The 28th International Joint Conference on Artificial Intelligence (IJCAI)",
publisher = "IJCAI",

}

RIS

TY - GEN

T1 - Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

AU - Wu, Yuting

AU - Liu, Xiao

AU - Feng, Yansong

AU - Wang, Zheng

AU - Yan, Rui

AU - Zhao, Dongyan

PY - 2019/7/31

Y1 - 2019/7/31

N2 - Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.

AB - Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.

U2 - 10.24963/ijcai.2019/733

DO - 10.24963/ijcai.2019/733

M3 - Conference contribution/Paper

SP - 5278

EP - 5284

BT - The 28th International Joint Conference on Artificial Intelligence (IJCAI)

PB - IJCAI

ER -