Abstract

Latent factor models have become a prevalent method in recom-mender systems, to predict users' preference on items based on the historical user feedback. Most of the existing methods, explicitly or implicitly, are built upon the first-order rating distance principle, which aims to minimize the difference between the estimated and real ratings. In this paper, we generalize such first-order rating distance principle and propose a new latent factor model (HOORAYS) FOR recommender systems. The core idea of the proposed method is to explore high-order rating distance, which aims to minimize not only (i) the difference between the estimated and real ratings of the same (user, item) pair (i.e., the first-order rating distance), but also (ii) the difference between the estimated and real rating difference of the same user across different items (i.e., the second-order rating distance). We formulate it as a regularized optimization problem, and propose an effective and scalable algorithm to solve it. Our analysis from the geometry and Bayesian perspectives indicate that by exploring the high-order rating distance, it helps to reduce the variance of the estimator, which in turns leads to better generalization performance (e.g., smaller prediction error). We evaluate the proposed method on four real-world data sets, two with explicit user feedback and the other two with implicit user feedback. Experimental results show that the proposed method consistently outperforms the state-of-the-art methods in terms of the prediction accuracy.

Original languageEnglish (US)
Title of host publicationKDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages525-534
Number of pages10
VolumePart F129685
ISBN (Electronic)9781450348874
DOIs
StatePublished - Aug 13 2017
Event23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017 - Halifax, Canada
Duration: Aug 13 2017Aug 17 2017

Other

Other23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017
CountryCanada
CityHalifax
Period8/13/178/17/17

Fingerprint

Recommender systems
Feedback
Geometry

Keywords

  • Collaborative filtering
  • High-order distance
  • Latent factor model
  • Recommender systems

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Xu, J., Yao, Y., Tong, H., Tao, X., & Lu, J. (2017). HoORaYs: High-order optimization of rating distance for recommender systems. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Vol. Part F129685, pp. 525-534). Association for Computing Machinery. https://doi.org/10.1145/3097983.3098019

HoORaYs : High-order optimization of rating distance for recommender systems. / Xu, Jingwei; Yao, Yuan; Tong, Hanghang; Tao, Xianping; Lu, Jian.

KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685 Association for Computing Machinery, 2017. p. 525-534.

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

Xu, J, Yao, Y, Tong, H, Tao, X & Lu, J 2017, HoORaYs: High-order optimization of rating distance for recommender systems. in KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. vol. Part F129685, Association for Computing Machinery, pp. 525-534, 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017, Halifax, Canada, 8/13/17. https://doi.org/10.1145/3097983.3098019
Xu J, Yao Y, Tong H, Tao X, Lu J. HoORaYs: High-order optimization of rating distance for recommender systems. In KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685. Association for Computing Machinery. 2017. p. 525-534 https://doi.org/10.1145/3097983.3098019
Xu, Jingwei ; Yao, Yuan ; Tong, Hanghang ; Tao, Xianping ; Lu, Jian. / HoORaYs : High-order optimization of rating distance for recommender systems. KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Vol. Part F129685 Association for Computing Machinery, 2017. pp. 525-534
@inproceedings{294cd5be9b914c73ad924113534364e4,
title = "HoORaYs: High-order optimization of rating distance for recommender systems",
abstract = "Latent factor models have become a prevalent method in recom-mender systems, to predict users' preference on items based on the historical user feedback. Most of the existing methods, explicitly or implicitly, are built upon the first-order rating distance principle, which aims to minimize the difference between the estimated and real ratings. In this paper, we generalize such first-order rating distance principle and propose a new latent factor model (HOORAYS) FOR recommender systems. The core idea of the proposed method is to explore high-order rating distance, which aims to minimize not only (i) the difference between the estimated and real ratings of the same (user, item) pair (i.e., the first-order rating distance), but also (ii) the difference between the estimated and real rating difference of the same user across different items (i.e., the second-order rating distance). We formulate it as a regularized optimization problem, and propose an effective and scalable algorithm to solve it. Our analysis from the geometry and Bayesian perspectives indicate that by exploring the high-order rating distance, it helps to reduce the variance of the estimator, which in turns leads to better generalization performance (e.g., smaller prediction error). We evaluate the proposed method on four real-world data sets, two with explicit user feedback and the other two with implicit user feedback. Experimental results show that the proposed method consistently outperforms the state-of-the-art methods in terms of the prediction accuracy.",
keywords = "Collaborative filtering, High-order distance, Latent factor model, Recommender systems",
author = "Jingwei Xu and Yuan Yao and Hanghang Tong and Xianping Tao and Jian Lu",
year = "2017",
month = "8",
day = "13",
doi = "10.1145/3097983.3098019",
language = "English (US)",
volume = "Part F129685",
pages = "525--534",
booktitle = "KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - HoORaYs

T2 - High-order optimization of rating distance for recommender systems

AU - Xu, Jingwei

AU - Yao, Yuan

AU - Tong, Hanghang

AU - Tao, Xianping

AU - Lu, Jian

PY - 2017/8/13

Y1 - 2017/8/13

N2 - Latent factor models have become a prevalent method in recom-mender systems, to predict users' preference on items based on the historical user feedback. Most of the existing methods, explicitly or implicitly, are built upon the first-order rating distance principle, which aims to minimize the difference between the estimated and real ratings. In this paper, we generalize such first-order rating distance principle and propose a new latent factor model (HOORAYS) FOR recommender systems. The core idea of the proposed method is to explore high-order rating distance, which aims to minimize not only (i) the difference between the estimated and real ratings of the same (user, item) pair (i.e., the first-order rating distance), but also (ii) the difference between the estimated and real rating difference of the same user across different items (i.e., the second-order rating distance). We formulate it as a regularized optimization problem, and propose an effective and scalable algorithm to solve it. Our analysis from the geometry and Bayesian perspectives indicate that by exploring the high-order rating distance, it helps to reduce the variance of the estimator, which in turns leads to better generalization performance (e.g., smaller prediction error). We evaluate the proposed method on four real-world data sets, two with explicit user feedback and the other two with implicit user feedback. Experimental results show that the proposed method consistently outperforms the state-of-the-art methods in terms of the prediction accuracy.

AB - Latent factor models have become a prevalent method in recom-mender systems, to predict users' preference on items based on the historical user feedback. Most of the existing methods, explicitly or implicitly, are built upon the first-order rating distance principle, which aims to minimize the difference between the estimated and real ratings. In this paper, we generalize such first-order rating distance principle and propose a new latent factor model (HOORAYS) FOR recommender systems. The core idea of the proposed method is to explore high-order rating distance, which aims to minimize not only (i) the difference between the estimated and real ratings of the same (user, item) pair (i.e., the first-order rating distance), but also (ii) the difference between the estimated and real rating difference of the same user across different items (i.e., the second-order rating distance). We formulate it as a regularized optimization problem, and propose an effective and scalable algorithm to solve it. Our analysis from the geometry and Bayesian perspectives indicate that by exploring the high-order rating distance, it helps to reduce the variance of the estimator, which in turns leads to better generalization performance (e.g., smaller prediction error). We evaluate the proposed method on four real-world data sets, two with explicit user feedback and the other two with implicit user feedback. Experimental results show that the proposed method consistently outperforms the state-of-the-art methods in terms of the prediction accuracy.

KW - Collaborative filtering

KW - High-order distance

KW - Latent factor model

KW - Recommender systems

UR - http://www.scopus.com/inward/record.url?scp=85029066159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029066159&partnerID=8YFLogxK

U2 - 10.1145/3097983.3098019

DO - 10.1145/3097983.3098019

M3 - Conference contribution

AN - SCOPUS:85029066159

VL - Part F129685

SP - 525

EP - 534

BT - KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -