Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing

Yongrui Qin, Lianyong Qi, Haolong Xiang, Wanchun Dou, Chi Yang, Xuyun Zhang

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

15 Citations (Scopus)

Abstract

With the advent of IoT (Internet of Things) age, considerable web services are emerging rapidly in service communities, which places a heavy burden on the target users' service selection decisions. In this situation, various techniques, e.g., collaborative filtering (i.e., CF) is introduced in service recommendation to alleviate the service selection burden. However, traditional CF-based service recommendation approaches often assume that the historical user-service quality data is centralized, while neglect the distributed recommendation situation. Generally, distributed service recommendation involves inevitable message communication among different parties and hence, brings challenging efficiency and privacy concerns. In view of this challenge, a novel privacy-preserving distributed service recommendation approach based on Locality-Sensitive Hashing (LSH), i.e., DistSRLSH is put forward in this paper. Through LSH, DistSRLSH can achieve a good tradeoff among service recommendation accuracy, privacy-preservation and efficiency in distributed environment. Finally, through a set of experiments deployed on WS-DREAM dataset, we validate the feasibility of our proposal in handling distributed service recommendation problems.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages49-56
Number of pages8
ISBN (Electronic)9781538607527
DOIs
Publication statusPublished - 7 Sep 2017
Event24th IEEE International Conference on Web Services - Honolulu, United States
Duration: 25 Jun 201730 Jun 2017
Conference number: 24
http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=60030&copyownerid=94650 (Link to Conference Details)

Conference

Conference24th IEEE International Conference on Web Services
Abbreviated titleICWS 2017
CountryUnited States
CityHonolulu
Period25/06/1730/06/17
Internet address

Fingerprint

Collaborative filtering
Web services
Communication
Experiments
Locality
Privacy preserving
Internet of things
Service selection
Burden

Cite this

Qin, Y., Qi, L., Xiang, H., Dou, W., Yang, C., & Zhang, X. (2017). Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing. In Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017 (pp. 49-56). [8029744] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICWS.2017.15
Qin, Yongrui ; Qi, Lianyong ; Xiang, Haolong ; Dou, Wanchun ; Yang, Chi ; Zhang, Xuyun. / Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing. Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 49-56
@inproceedings{f67837ffd0dd48b4a97983b2f5cd71bd,
title = "Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing",
abstract = "With the advent of IoT (Internet of Things) age, considerable web services are emerging rapidly in service communities, which places a heavy burden on the target users' service selection decisions. In this situation, various techniques, e.g., collaborative filtering (i.e., CF) is introduced in service recommendation to alleviate the service selection burden. However, traditional CF-based service recommendation approaches often assume that the historical user-service quality data is centralized, while neglect the distributed recommendation situation. Generally, distributed service recommendation involves inevitable message communication among different parties and hence, brings challenging efficiency and privacy concerns. In view of this challenge, a novel privacy-preserving distributed service recommendation approach based on Locality-Sensitive Hashing (LSH), i.e., DistSRLSH is put forward in this paper. Through LSH, DistSRLSH can achieve a good tradeoff among service recommendation accuracy, privacy-preservation and efficiency in distributed environment. Finally, through a set of experiments deployed on WS-DREAM dataset, we validate the feasibility of our proposal in handling distributed service recommendation problems.",
keywords = "Collaborative Filtering, Distributed Service Recommendation, Efficiency, Locality Sensitive Hashing, Privacy",
author = "Yongrui Qin and Lianyong Qi and Haolong Xiang and Wanchun Dou and Chi Yang and Xuyun Zhang",
year = "2017",
month = "9",
day = "7",
doi = "10.1109/ICWS.2017.15",
language = "English",
pages = "49--56",
booktitle = "Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Qin, Y, Qi, L, Xiang, H, Dou, W, Yang, C & Zhang, X 2017, Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing. in Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017., 8029744, Institute of Electrical and Electronics Engineers Inc., pp. 49-56, 24th IEEE International Conference on Web Services, Honolulu, United States, 25/06/17. https://doi.org/10.1109/ICWS.2017.15

Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing. / Qin, Yongrui; Qi, Lianyong; Xiang, Haolong; Dou, Wanchun; Yang, Chi; Zhang, Xuyun.

Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 49-56 8029744.

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

TY - GEN

T1 - Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing

AU - Qin, Yongrui

AU - Qi, Lianyong

AU - Xiang, Haolong

AU - Dou, Wanchun

AU - Yang, Chi

AU - Zhang, Xuyun

PY - 2017/9/7

Y1 - 2017/9/7

N2 - With the advent of IoT (Internet of Things) age, considerable web services are emerging rapidly in service communities, which places a heavy burden on the target users' service selection decisions. In this situation, various techniques, e.g., collaborative filtering (i.e., CF) is introduced in service recommendation to alleviate the service selection burden. However, traditional CF-based service recommendation approaches often assume that the historical user-service quality data is centralized, while neglect the distributed recommendation situation. Generally, distributed service recommendation involves inevitable message communication among different parties and hence, brings challenging efficiency and privacy concerns. In view of this challenge, a novel privacy-preserving distributed service recommendation approach based on Locality-Sensitive Hashing (LSH), i.e., DistSRLSH is put forward in this paper. Through LSH, DistSRLSH can achieve a good tradeoff among service recommendation accuracy, privacy-preservation and efficiency in distributed environment. Finally, through a set of experiments deployed on WS-DREAM dataset, we validate the feasibility of our proposal in handling distributed service recommendation problems.

AB - With the advent of IoT (Internet of Things) age, considerable web services are emerging rapidly in service communities, which places a heavy burden on the target users' service selection decisions. In this situation, various techniques, e.g., collaborative filtering (i.e., CF) is introduced in service recommendation to alleviate the service selection burden. However, traditional CF-based service recommendation approaches often assume that the historical user-service quality data is centralized, while neglect the distributed recommendation situation. Generally, distributed service recommendation involves inevitable message communication among different parties and hence, brings challenging efficiency and privacy concerns. In view of this challenge, a novel privacy-preserving distributed service recommendation approach based on Locality-Sensitive Hashing (LSH), i.e., DistSRLSH is put forward in this paper. Through LSH, DistSRLSH can achieve a good tradeoff among service recommendation accuracy, privacy-preservation and efficiency in distributed environment. Finally, through a set of experiments deployed on WS-DREAM dataset, we validate the feasibility of our proposal in handling distributed service recommendation problems.

KW - Collaborative Filtering

KW - Distributed Service Recommendation

KW - Efficiency

KW - Locality Sensitive Hashing

KW - Privacy

UR - http://www.scopus.com/inward/record.url?scp=85032369005&partnerID=8YFLogxK

U2 - 10.1109/ICWS.2017.15

DO - 10.1109/ICWS.2017.15

M3 - Conference contribution

SP - 49

EP - 56

BT - Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Qin Y, Qi L, Xiang H, Dou W, Yang C, Zhang X. Privacy-Preserving Distributed Service Recommendation Based on Locality-Sensitive Hashing. In Proceedings - 2017 IEEE 24th International Conference on Web Services, ICWS 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 49-56. 8029744 https://doi.org/10.1109/ICWS.2017.15