Dual neural personalized ranking

Seunghyeon Kim, Jongwuk Lee, Hyunjung Shim

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

Abstract

Implicit user feedback is a fundamental dataset for personalized recommendation models. Because of its inherent characteristics of sparse one-class values, it is challenging to uncover meaningful user/item representations. In this paper, we propose dual neural personalized ranking (DualNPR), which fully exploits both user- and item-side pairwise rankings in a unified manner. The key novelties of the proposed model are three-fold: (1) DualNPR discovers mutual correlation among users and items by utilizing both user- and item-side pairwise rankings, alleviating the data sparsity problem. We stress that, unlike existing models that require extra information, DualNPR naturally augments both user- and item-side pairwise rankings from a user-item interaction matrix. (2) DualNPR is built upon deep matrix factorization to capture the variability of user/item representations. In particular, it chooses raw user/item vectors as an input and learns latent user/item representations effectively. (3) DualNPR employs a dynamic negative sampling method using an exponential function, further improving the accuracy of top-N recommendation. In experimental results over three benchmark datasets, DualNPR outperforms baseline models by 21.9-86.7% in hit rate, 14.5-105.8% in normalized discounted cumulative gain, and 5.1-23.3% in the area under the ROC curve.

Original languageEnglish
Title of host publicationThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PublisherAssociation for Computing Machinery, Inc
Pages863-873
Number of pages11
ISBN (Electronic)9781450366748
DOIs
Publication statusPublished - 2019 May 13
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: 2019 May 132019 May 17

Publication series

NameThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

Conference

Conference2019 World Wide Web Conference, WWW 2019
CountryUnited States
CitySan Francisco
Period19/5/1319/5/17

Fingerprint

Exponential functions
Factorization
Sampling
Feedback

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software

Cite this

Kim, S., Lee, J., & Shim, H. (2019). Dual neural personalized ranking. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (pp. 863-873). (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308558.3313585
Kim, Seunghyeon ; Lee, Jongwuk ; Shim, Hyunjung. / Dual neural personalized ranking. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. pp. 863-873 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).
@inproceedings{fd531c8d73c1435787c439e3c9a8d8ef,
title = "Dual neural personalized ranking",
abstract = "Implicit user feedback is a fundamental dataset for personalized recommendation models. Because of its inherent characteristics of sparse one-class values, it is challenging to uncover meaningful user/item representations. In this paper, we propose dual neural personalized ranking (DualNPR), which fully exploits both user- and item-side pairwise rankings in a unified manner. The key novelties of the proposed model are three-fold: (1) DualNPR discovers mutual correlation among users and items by utilizing both user- and item-side pairwise rankings, alleviating the data sparsity problem. We stress that, unlike existing models that require extra information, DualNPR naturally augments both user- and item-side pairwise rankings from a user-item interaction matrix. (2) DualNPR is built upon deep matrix factorization to capture the variability of user/item representations. In particular, it chooses raw user/item vectors as an input and learns latent user/item representations effectively. (3) DualNPR employs a dynamic negative sampling method using an exponential function, further improving the accuracy of top-N recommendation. In experimental results over three benchmark datasets, DualNPR outperforms baseline models by 21.9-86.7{\%} in hit rate, 14.5-105.8{\%} in normalized discounted cumulative gain, and 5.1-23.3{\%} in the area under the ROC curve.",
author = "Seunghyeon Kim and Jongwuk Lee and Hyunjung Shim",
year = "2019",
month = "5",
day = "13",
doi = "10.1145/3308558.3313585",
language = "English",
series = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",
publisher = "Association for Computing Machinery, Inc",
pages = "863--873",
booktitle = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",

}

Kim, S, Lee, J & Shim, H 2019, Dual neural personalized ranking. in The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019, Association for Computing Machinery, Inc, pp. 863-873, 2019 World Wide Web Conference, WWW 2019, San Francisco, United States, 19/5/13. https://doi.org/10.1145/3308558.3313585

Dual neural personalized ranking. / Kim, Seunghyeon; Lee, Jongwuk; Shim, Hyunjung.

The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 863-873 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).

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

TY - GEN

T1 - Dual neural personalized ranking

AU - Kim, Seunghyeon

AU - Lee, Jongwuk

AU - Shim, Hyunjung

PY - 2019/5/13

Y1 - 2019/5/13

N2 - Implicit user feedback is a fundamental dataset for personalized recommendation models. Because of its inherent characteristics of sparse one-class values, it is challenging to uncover meaningful user/item representations. In this paper, we propose dual neural personalized ranking (DualNPR), which fully exploits both user- and item-side pairwise rankings in a unified manner. The key novelties of the proposed model are three-fold: (1) DualNPR discovers mutual correlation among users and items by utilizing both user- and item-side pairwise rankings, alleviating the data sparsity problem. We stress that, unlike existing models that require extra information, DualNPR naturally augments both user- and item-side pairwise rankings from a user-item interaction matrix. (2) DualNPR is built upon deep matrix factorization to capture the variability of user/item representations. In particular, it chooses raw user/item vectors as an input and learns latent user/item representations effectively. (3) DualNPR employs a dynamic negative sampling method using an exponential function, further improving the accuracy of top-N recommendation. In experimental results over three benchmark datasets, DualNPR outperforms baseline models by 21.9-86.7% in hit rate, 14.5-105.8% in normalized discounted cumulative gain, and 5.1-23.3% in the area under the ROC curve.

AB - Implicit user feedback is a fundamental dataset for personalized recommendation models. Because of its inherent characteristics of sparse one-class values, it is challenging to uncover meaningful user/item representations. In this paper, we propose dual neural personalized ranking (DualNPR), which fully exploits both user- and item-side pairwise rankings in a unified manner. The key novelties of the proposed model are three-fold: (1) DualNPR discovers mutual correlation among users and items by utilizing both user- and item-side pairwise rankings, alleviating the data sparsity problem. We stress that, unlike existing models that require extra information, DualNPR naturally augments both user- and item-side pairwise rankings from a user-item interaction matrix. (2) DualNPR is built upon deep matrix factorization to capture the variability of user/item representations. In particular, it chooses raw user/item vectors as an input and learns latent user/item representations effectively. (3) DualNPR employs a dynamic negative sampling method using an exponential function, further improving the accuracy of top-N recommendation. In experimental results over three benchmark datasets, DualNPR outperforms baseline models by 21.9-86.7% in hit rate, 14.5-105.8% in normalized discounted cumulative gain, and 5.1-23.3% in the area under the ROC curve.

UR - http://www.scopus.com/inward/record.url?scp=85066911950&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066911950&partnerID=8YFLogxK

U2 - 10.1145/3308558.3313585

DO - 10.1145/3308558.3313585

M3 - Conference contribution

AN - SCOPUS:85066911950

T3 - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

SP - 863

EP - 873

BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019

PB - Association for Computing Machinery, Inc

ER -

Kim S, Lee J, Shim H. Dual neural personalized ranking. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc. 2019. p. 863-873. (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). https://doi.org/10.1145/3308558.3313585