Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks

Junxin Chen; Kuijie Lin; Xiang Chen; Xijun Wang; Terng Yin Hsu

doi:10.1007/978-981-99-3925-1_5

Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks

Junxin Chen, Kuijie Lin, Xiang Chen^*, Xijun Wang, Terng Yin Hsu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Personalized location recommendation plays a very important role in location-based social networks, from which both users and service providers can benefit from. In spite of the significant endeavors that have been made towards acquiring knowledge on location attributes and user inclinations, it is still faced with serious data sparsity problems. In this paper, we propose a personalized location recommendation model based on graph neural networks with multi-view learning to obtain effective representations of mobile users and locations from different heterogeneous graphs. We also design an attention-enhanced mechanism to explore the implicit interactions between mobile users and locations themselves. Conducting adequate comparative experiments on two real-world telecom datasets has demonstrated that our model achieves superior performance. Additionally, our model has been proven effective in addressing data sparsity issues.

Original language	English
Title of host publication	Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings
Editors	Xiaofeng Meng, Yang Chen, Liming Suo, Qi Xuan, Zi-Ke Zhang
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	83-95
Number of pages	13
ISBN (Print)	9789819939244
DOIs	https://doi.org/10.1007/978-981-99-3925-1_5
State	Published - 2023
Event	8th China National Conference on Big Data and Social Computing, BDSC 2023 - Urumqi, China Duration: 15 Jul 2023 → 17 Jul 2023

Publication series

Name	Communications in Computer and Information Science
Volume	1846 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	8th China National Conference on Big Data and Social Computing, BDSC 2023
Country/Territory	China
City	Urumqi
Period	15/07/23 → 17/07/23

Keywords

Data Sparsity
Graph Neural Networks
Location Recommendation
Multi-view Learning

Access to Document

10.1007/978-981-99-3925-1_5

Cite this

Chen, J., Lin, K., Chen, X., Wang, X., & Hsu, T. Y. (2023). Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks. In X. Meng, Y. Chen, L. Suo, Q. Xuan, & Z.-K. Zhang (Eds.), Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings (pp. 83-95). (Communications in Computer and Information Science; Vol. 1846 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-3925-1_5

Chen, Junxin ; Lin, Kuijie ; Chen, Xiang et al. / Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks. Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings. editor / Xiaofeng Meng ; Yang Chen ; Liming Suo ; Qi Xuan ; Zi-Ke Zhang. Springer Science and Business Media Deutschland GmbH, 2023. pp. 83-95 (Communications in Computer and Information Science).

@inproceedings{cb733993c1cc46ce80379a8bdcd55d65,

title = "Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks",

abstract = "Personalized location recommendation plays a very important role in location-based social networks, from which both users and service providers can benefit from. In spite of the significant endeavors that have been made towards acquiring knowledge on location attributes and user inclinations, it is still faced with serious data sparsity problems. In this paper, we propose a personalized location recommendation model based on graph neural networks with multi-view learning to obtain effective representations of mobile users and locations from different heterogeneous graphs. We also design an attention-enhanced mechanism to explore the implicit interactions between mobile users and locations themselves. Conducting adequate comparative experiments on two real-world telecom datasets has demonstrated that our model achieves superior performance. Additionally, our model has been proven effective in addressing data sparsity issues.",

keywords = "Data Sparsity, Graph Neural Networks, Location Recommendation, Multi-view Learning",

author = "Junxin Chen and Kuijie Lin and Xiang Chen and Xijun Wang and Hsu, {Terng Yin}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 8th China National Conference on Big Data and Social Computing, BDSC 2023 ; Conference date: 15-07-2023 Through 17-07-2023",

year = "2023",

doi = "10.1007/978-981-99-3925-1_5",

language = "English",

isbn = "9789819939244",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "83--95",

editor = "Xiaofeng Meng and Yang Chen and Liming Suo and Qi Xuan and Zi-Ke Zhang",

booktitle = "Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings",

address = "德國",

}

Chen, J, Lin, K, Chen, X, Wang, X & Hsu, TY 2023, Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks. in X Meng, Y Chen, L Suo, Q Xuan & Z-K Zhang (eds), Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings. Communications in Computer and Information Science, vol. 1846 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 83-95, 8th China National Conference on Big Data and Social Computing, BDSC 2023, Urumqi, China, 15/07/23. https://doi.org/10.1007/978-981-99-3925-1_5

Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks. / Chen, Junxin; Lin, Kuijie; Chen, Xiang et al.
Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings. ed. / Xiaofeng Meng; Yang Chen; Liming Suo; Qi Xuan; Zi-Ke Zhang. Springer Science and Business Media Deutschland GmbH, 2023. p. 83-95 (Communications in Computer and Information Science; Vol. 1846 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks

AU - Chen, Junxin

AU - Lin, Kuijie

AU - Chen, Xiang

AU - Wang, Xijun

AU - Hsu, Terng Yin

PY - 2023

Y1 - 2023

N2 - Personalized location recommendation plays a very important role in location-based social networks, from which both users and service providers can benefit from. In spite of the significant endeavors that have been made towards acquiring knowledge on location attributes and user inclinations, it is still faced with serious data sparsity problems. In this paper, we propose a personalized location recommendation model based on graph neural networks with multi-view learning to obtain effective representations of mobile users and locations from different heterogeneous graphs. We also design an attention-enhanced mechanism to explore the implicit interactions between mobile users and locations themselves. Conducting adequate comparative experiments on two real-world telecom datasets has demonstrated that our model achieves superior performance. Additionally, our model has been proven effective in addressing data sparsity issues.

AB - Personalized location recommendation plays a very important role in location-based social networks, from which both users and service providers can benefit from. In spite of the significant endeavors that have been made towards acquiring knowledge on location attributes and user inclinations, it is still faced with serious data sparsity problems. In this paper, we propose a personalized location recommendation model based on graph neural networks with multi-view learning to obtain effective representations of mobile users and locations from different heterogeneous graphs. We also design an attention-enhanced mechanism to explore the implicit interactions between mobile users and locations themselves. Conducting adequate comparative experiments on two real-world telecom datasets has demonstrated that our model achieves superior performance. Additionally, our model has been proven effective in addressing data sparsity issues.

KW - Data Sparsity

KW - Graph Neural Networks

KW - Location Recommendation

KW - Multi-view Learning

UR - http://www.scopus.com/inward/record.url?scp=85168768474&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-3925-1_5

DO - 10.1007/978-981-99-3925-1_5

M3 - Conference contribution

AN - SCOPUS:85168768474

SN - 9789819939244

T3 - Communications in Computer and Information Science

SP - 83

EP - 95

BT - Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings

A2 - Meng, Xiaofeng

A2 - Chen, Yang

A2 - Suo, Liming

A2 - Xuan, Qi

A2 - Zhang, Zi-Ke

PB - Springer Science and Business Media Deutschland GmbH

T2 - 8th China National Conference on Big Data and Social Computing, BDSC 2023

Y2 - 15 July 2023 through 17 July 2023

ER -

Chen J, Lin K, Chen X, Wang X, Hsu TY. Location Recommendations Based on Multi-view Learning and Attention-Enhanced Graph Networks. In Meng X, Chen Y, Suo L, Xuan Q, Zhang ZK, editors, Big Data and Social Computing - 8th China National Conference, BDSC 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 83-95. (Communications in Computer and Information Science). doi: 10.1007/978-981-99-3925-1_5