A side information enhanced matrix factorization approach via hierarchical generalized linear model

Dora D. Liu, Zhong Yuan Lai*, Usman Naseem

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Matrix factorization (MF) is a popular method for collaborative filtering. Recently, more and more MF methods have been proposed to incorporate side information. However, most of them are vulnerable to changes in data or sub-models. Moreover, data often follows a Pareto distribution and such an imbalance of data leads to a biased global mean, affecting the prediction accuracy. To overcome these defects, we designed a Hierarchical Generalized Linear Model-based MF method (HGLMMF) which can leverage both the original and processed side information. More specifically, HGLMMF utilizes one portion of the side information to construct covariates for fixed effects and the other portion to model the cluster-specific effects to adjust the global-bias problem. In fact, a number of state-of-the-art MF models can be viewed as special cases of HGLMMF. The obtained prediction results from experiments prove that HGLMMF is highly competitive with state-of-the-art methods.

Original languageEnglish
Title of host publication2022 IEEE 9th International Conference on Data Science and Advanced Analytics DSAA'2022
Subtitle of host publicationproceedings
EditorsJoshua Zhexue Huang, Yi Pan, Barbara Hammer, Muhammad Khurram Khan, Xing Xie, Laizhong Cui, Yulin He
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages9
ISBN (Electronic)9781665473309
ISBN (Print)9781665473316
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022 - Shenzhen, China
Duration: 13 Oct 202216 Oct 2022

Conference

Conference9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022
Country/TerritoryChina
CityShenzhen
Period13/10/2216/10/22

Keywords

  • matrix factorization
  • hierarchical generalized linear mixed model
  • side information
  • cold start
  • recommender systems

Fingerprint

Dive into the research topics of 'A side information enhanced matrix factorization approach via hierarchical generalized linear model'. Together they form a unique fingerprint.

Cite this