Adaptive matrix completion for the users and the items in tail

Mohit Sharma, George Karypis

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

Abstract

Recommender systems are widely used to recommend the most appealing items to users. These recommendations can be generated by applying collaborative filtering methods. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. In this work, we show that the skewed distribution of ratings in the user-item rating matrix of real-world datasets affects the accuracy of matrix-completion-based approaches. Also, we show that the number of ratings that an item or a user has positively correlates with the ability of low-rank matrix-completion-based approaches to predict the ratings for the item or the user accurately. Furthermore, we use these insights to develop four matrix completion-based approaches, i.e., Frequency Adaptive Rating Prediction (FARP), Truncated Matrix Factorization (TMF), Truncated Matrix Factorization with Dropout (TMF + Dropout) and Inverse Frequency Weighted Matrix Factorization (IFWMF), that outperforms traditional matrix-completion-based approaches for the users and the items with few ratings in the user-item rating matrix.

Original languageEnglish (US)
Title of host publicationThe Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PublisherAssociation for Computing Machinery, Inc
Pages3223-3229
Number of pages7
ISBN (Electronic)9781450366748
DOIs
StatePublished - May 13 2019
Event2019 World Wide Web Conference, WWW 2019 - San Francisco, United States
Duration: May 13 2019May 17 2019

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
Period5/13/195/17/19

Fingerprint

Factorization
Collaborative filtering
Recommender systems

Keywords

  • Collaborative filtering
  • Matrix completion
  • Matrix factorization
  • Recommender systems

Cite this

Sharma, M., & Karypis, G. (2019). Adaptive matrix completion for the users and the items in tail. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (pp. 3223-3229). (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3308558.3313736

Adaptive matrix completion for the users and the items in tail. / Sharma, Mohit; Karypis, George.

The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 3223-3229 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).

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

Sharma, M & Karypis, G 2019, Adaptive matrix completion for the users and the items in tail. 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. 3223-3229, 2019 World Wide Web Conference, WWW 2019, San Francisco, United States, 5/13/19. https://doi.org/10.1145/3308558.3313736
Sharma M, Karypis G. Adaptive matrix completion for the users and the items in tail. In The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc. 2019. p. 3223-3229. (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019). https://doi.org/10.1145/3308558.3313736
Sharma, Mohit ; Karypis, George. / Adaptive matrix completion for the users and the items in tail. The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. pp. 3223-3229 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).
@inproceedings{b378658586fe47448ff1a69582f1e46b,
title = "Adaptive matrix completion for the users and the items in tail",
abstract = "Recommender systems are widely used to recommend the most appealing items to users. These recommendations can be generated by applying collaborative filtering methods. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. In this work, we show that the skewed distribution of ratings in the user-item rating matrix of real-world datasets affects the accuracy of matrix-completion-based approaches. Also, we show that the number of ratings that an item or a user has positively correlates with the ability of low-rank matrix-completion-based approaches to predict the ratings for the item or the user accurately. Furthermore, we use these insights to develop four matrix completion-based approaches, i.e., Frequency Adaptive Rating Prediction (FARP), Truncated Matrix Factorization (TMF), Truncated Matrix Factorization with Dropout (TMF + Dropout) and Inverse Frequency Weighted Matrix Factorization (IFWMF), that outperforms traditional matrix-completion-based approaches for the users and the items with few ratings in the user-item rating matrix.",
keywords = "Collaborative filtering, Matrix completion, Matrix factorization, Recommender systems",
author = "Mohit Sharma and George Karypis",
year = "2019",
month = "5",
day = "13",
doi = "10.1145/3308558.3313736",
language = "English (US)",
series = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",
publisher = "Association for Computing Machinery, Inc",
pages = "3223--3229",
booktitle = "The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019",

}

TY - GEN

T1 - Adaptive matrix completion for the users and the items in tail

AU - Sharma, Mohit

AU - Karypis, George

PY - 2019/5/13

Y1 - 2019/5/13

N2 - Recommender systems are widely used to recommend the most appealing items to users. These recommendations can be generated by applying collaborative filtering methods. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. In this work, we show that the skewed distribution of ratings in the user-item rating matrix of real-world datasets affects the accuracy of matrix-completion-based approaches. Also, we show that the number of ratings that an item or a user has positively correlates with the ability of low-rank matrix-completion-based approaches to predict the ratings for the item or the user accurately. Furthermore, we use these insights to develop four matrix completion-based approaches, i.e., Frequency Adaptive Rating Prediction (FARP), Truncated Matrix Factorization (TMF), Truncated Matrix Factorization with Dropout (TMF + Dropout) and Inverse Frequency Weighted Matrix Factorization (IFWMF), that outperforms traditional matrix-completion-based approaches for the users and the items with few ratings in the user-item rating matrix.

AB - Recommender systems are widely used to recommend the most appealing items to users. These recommendations can be generated by applying collaborative filtering methods. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. In this work, we show that the skewed distribution of ratings in the user-item rating matrix of real-world datasets affects the accuracy of matrix-completion-based approaches. Also, we show that the number of ratings that an item or a user has positively correlates with the ability of low-rank matrix-completion-based approaches to predict the ratings for the item or the user accurately. Furthermore, we use these insights to develop four matrix completion-based approaches, i.e., Frequency Adaptive Rating Prediction (FARP), Truncated Matrix Factorization (TMF), Truncated Matrix Factorization with Dropout (TMF + Dropout) and Inverse Frequency Weighted Matrix Factorization (IFWMF), that outperforms traditional matrix-completion-based approaches for the users and the items with few ratings in the user-item rating matrix.

KW - Collaborative filtering

KW - Matrix completion

KW - Matrix factorization

KW - Recommender systems

UR - http://www.scopus.com/inward/record.url?scp=85066909867&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066909867&partnerID=8YFLogxK

U2 - 10.1145/3308558.3313736

DO - 10.1145/3308558.3313736

M3 - Conference contribution

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

SP - 3223

EP - 3229

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

PB - Association for Computing Machinery, Inc

ER -