Attention-based multi-hop reasoning for knowledge graph

Zikang Wang, Linjing Li, Dajun Zeng, Yue Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Knowledge graph plays an important role in detection, prediction, early warning, and other security related applications. A fundamental task in applying knowledge graph is the so-called multi-hop reasoning, which focuses on inferring new relations between entities. In this paper, we introduce attention mechanism to the classic compositional method. After finding reasoning paths between entities, we aggregate these paths' embeddings into one according to their attentions, and infer the relation of entities based on the combined embedding. Two experiments on NELL-995 dataset, fact prediction and link prediction, validated that our method outperforms all baselines.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018
EditorsDongwon Lee, Ghita Mezzour, Ponnurangam Kumaraguru, Nitesh Saxena
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages211-213
Number of pages3
ISBN (Electronic)9781538678480
DOIs
StatePublished - Dec 24 2018
Externally publishedYes
Event16th IEEE International Conference on Intelligence and Security Informatics, ISI 2018 - Miami, United States
Duration: Nov 9 2018Nov 11 2018

Other

Other16th IEEE International Conference on Intelligence and Security Informatics, ISI 2018
CountryUnited States
CityMiami
Period11/9/1811/11/18

Fingerprint

experiment
Prediction
Graph
Experiments
Early warning
Experiment

Keywords

  • Attention mechanism
  • Knowledge graph
  • Multi-hop reasoning
  • Random walking

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Communication

Cite this

Wang, Z., Li, L., Zeng, D., & Chen, Y. (2018). Attention-based multi-hop reasoning for knowledge graph. In D. Lee, G. Mezzour, P. Kumaraguru, & N. Saxena (Eds.), 2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018 (pp. 211-213). [8587330] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISI.2018.8587330

Attention-based multi-hop reasoning for knowledge graph. / Wang, Zikang; Li, Linjing; Zeng, Dajun; Chen, Yue.

2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018. ed. / Dongwon Lee; Ghita Mezzour; Ponnurangam Kumaraguru; Nitesh Saxena. Institute of Electrical and Electronics Engineers Inc., 2018. p. 211-213 8587330.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Z, Li, L, Zeng, D & Chen, Y 2018, Attention-based multi-hop reasoning for knowledge graph. in D Lee, G Mezzour, P Kumaraguru & N Saxena (eds), 2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018., 8587330, Institute of Electrical and Electronics Engineers Inc., pp. 211-213, 16th IEEE International Conference on Intelligence and Security Informatics, ISI 2018, Miami, United States, 11/9/18. https://doi.org/10.1109/ISI.2018.8587330
Wang Z, Li L, Zeng D, Chen Y. Attention-based multi-hop reasoning for knowledge graph. In Lee D, Mezzour G, Kumaraguru P, Saxena N, editors, 2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 211-213. 8587330 https://doi.org/10.1109/ISI.2018.8587330
Wang, Zikang ; Li, Linjing ; Zeng, Dajun ; Chen, Yue. / Attention-based multi-hop reasoning for knowledge graph. 2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018. editor / Dongwon Lee ; Ghita Mezzour ; Ponnurangam Kumaraguru ; Nitesh Saxena. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 211-213
@inproceedings{76e74ef69f86456e9a9f1061141540c9,
title = "Attention-based multi-hop reasoning for knowledge graph",
abstract = "Knowledge graph plays an important role in detection, prediction, early warning, and other security related applications. A fundamental task in applying knowledge graph is the so-called multi-hop reasoning, which focuses on inferring new relations between entities. In this paper, we introduce attention mechanism to the classic compositional method. After finding reasoning paths between entities, we aggregate these paths' embeddings into one according to their attentions, and infer the relation of entities based on the combined embedding. Two experiments on NELL-995 dataset, fact prediction and link prediction, validated that our method outperforms all baselines.",
keywords = "Attention mechanism, Knowledge graph, Multi-hop reasoning, Random walking",
author = "Zikang Wang and Linjing Li and Dajun Zeng and Yue Chen",
year = "2018",
month = "12",
day = "24",
doi = "10.1109/ISI.2018.8587330",
language = "English (US)",
pages = "211--213",
editor = "Dongwon Lee and Ghita Mezzour and Ponnurangam Kumaraguru and Nitesh Saxena",
booktitle = "2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Attention-based multi-hop reasoning for knowledge graph

AU - Wang, Zikang

AU - Li, Linjing

AU - Zeng, Dajun

AU - Chen, Yue

PY - 2018/12/24

Y1 - 2018/12/24

N2 - Knowledge graph plays an important role in detection, prediction, early warning, and other security related applications. A fundamental task in applying knowledge graph is the so-called multi-hop reasoning, which focuses on inferring new relations between entities. In this paper, we introduce attention mechanism to the classic compositional method. After finding reasoning paths between entities, we aggregate these paths' embeddings into one according to their attentions, and infer the relation of entities based on the combined embedding. Two experiments on NELL-995 dataset, fact prediction and link prediction, validated that our method outperforms all baselines.

AB - Knowledge graph plays an important role in detection, prediction, early warning, and other security related applications. A fundamental task in applying knowledge graph is the so-called multi-hop reasoning, which focuses on inferring new relations between entities. In this paper, we introduce attention mechanism to the classic compositional method. After finding reasoning paths between entities, we aggregate these paths' embeddings into one according to their attentions, and infer the relation of entities based on the combined embedding. Two experiments on NELL-995 dataset, fact prediction and link prediction, validated that our method outperforms all baselines.

KW - Attention mechanism

KW - Knowledge graph

KW - Multi-hop reasoning

KW - Random walking

UR - http://www.scopus.com/inward/record.url?scp=85061026555&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061026555&partnerID=8YFLogxK

U2 - 10.1109/ISI.2018.8587330

DO - 10.1109/ISI.2018.8587330

M3 - Conference contribution

AN - SCOPUS:85061026555

SP - 211

EP - 213

BT - 2018 IEEE International Conference on Intelligence and Security Informatics, ISI 2018

A2 - Lee, Dongwon

A2 - Mezzour, Ghita

A2 - Kumaraguru, Ponnurangam

A2 - Saxena, Nitesh

PB - Institute of Electrical and Electronics Engineers Inc.

ER -