Conjugate-prior-regularized multinomial pLSA for collaborative filtering

Marcus Klasson; Stefan Ingi Adalbjörnsson; Johan Swärd; Søren Vang Andersen

doi:10.23919/EUSIPCO.2017.8081661

Conjugate-prior-regularized multinomial pLSA for collaborative filtering

Marcus Klasson, Stefan Ingi Adalbjörnsson, Johan Swärd, Søren Vang Andersen

Lund University

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

Abstract

We consider the over-fitting problem for multinomial probabilistic Latent Semantic Analysis (pLSA) in collaborative filtering, using a regularization approach. For big data applications, the computational complexity is at a premium and we, therefore, consider a maximum a posteriori approach based on conjugate priors that ensure that complexity of each step remains the same as compared to the un-regularized method. In the numerical section, we show that the proposed regularization method and training scheme yields an improvement on commonly used data sets, as compared to previously proposed heuristics.

Original language	English
Title of host publication	25th European Signal Processing Conference, EUSIPCO 2017
Publisher	IEEE - Institute of Electrical and Electronics Engineers Inc.
Pages	2501-2505
Number of pages	5
Volume	2017-January
ISBN (Electronic)	9780992862671
DOIs	https://doi.org/10.23919/EUSIPCO.2017.8081661
Publication status	Published - 2017 Oct 23
Event	25th European Signal Processing Conference, EUSIPCO 2017 - Kos island, Kos, Greece Duration: 2017 Aug 28 → 2017 Sept 2

Conference

Conference	25th European Signal Processing Conference, EUSIPCO 2017
Country/Territory	Greece
City	Kos
Period	2017/08/28 → 2017/09/02

Subject classification (UKÄ)

Signal Processing

Free keywords

Collaborative filtering
Conjugate prior regularization
Probabilistic latent semantic analysis
Recommender systems

Access to Document

10.23919/EUSIPCO.2017.8081661

Cite this

@inproceedings{6eaaa5feb16e41cf9930f4968566e009,

title = "Conjugate-prior-regularized multinomial pLSA for collaborative filtering",

abstract = "We consider the over-fitting problem for multinomial probabilistic Latent Semantic Analysis (pLSA) in collaborative filtering, using a regularization approach. For big data applications, the computational complexity is at a premium and we, therefore, consider a maximum a posteriori approach based on conjugate priors that ensure that complexity of each step remains the same as compared to the un-regularized method. In the numerical section, we show that the proposed regularization method and training scheme yields an improvement on commonly used data sets, as compared to previously proposed heuristics.",

keywords = "Collaborative filtering, Conjugate prior regularization, Probabilistic latent semantic analysis, Recommender systems",

author = "Marcus Klasson and Adalbj{\"o}rnsson, {Stefan Ingi} and Johan Sw{\"a}rd and Andersen, {S{\o}ren Vang}",

year = "2017",

month = oct,

day = "23",

doi = "10.23919/EUSIPCO.2017.8081661",

language = "English",

volume = "2017-January",

pages = "2501--2505",

booktitle = "25th European Signal Processing Conference, EUSIPCO 2017",

publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "25th European Signal Processing Conference, EUSIPCO 2017 ; Conference date: 28-08-2017 Through 02-09-2017",

}

Klasson, M, Adalbjörnsson, SI, Swärd, J & Andersen, SV 2017, Conjugate-prior-regularized multinomial pLSA for collaborative filtering. in 25th European Signal Processing Conference, EUSIPCO 2017. vol. 2017-January, 8081661, IEEE - Institute of Electrical and Electronics Engineers Inc., pp. 2501-2505, 25th European Signal Processing Conference, EUSIPCO 2017, Kos, Greece, 2017/08/28. https://doi.org/10.23919/EUSIPCO.2017.8081661

Conjugate-prior-regularized multinomial pLSA for collaborative filtering. / Klasson, Marcus; Adalbjörnsson, Stefan Ingi; Swärd, Johan et al.
25th European Signal Processing Conference, EUSIPCO 2017. Vol. 2017-January IEEE - Institute of Electrical and Electronics Engineers Inc., 2017. p. 2501-2505 8081661.

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

TY - GEN

T1 - Conjugate-prior-regularized multinomial pLSA for collaborative filtering

AU - Klasson, Marcus

AU - Adalbjörnsson, Stefan Ingi

AU - Swärd, Johan

AU - Andersen, Søren Vang

PY - 2017/10/23

Y1 - 2017/10/23

N2 - We consider the over-fitting problem for multinomial probabilistic Latent Semantic Analysis (pLSA) in collaborative filtering, using a regularization approach. For big data applications, the computational complexity is at a premium and we, therefore, consider a maximum a posteriori approach based on conjugate priors that ensure that complexity of each step remains the same as compared to the un-regularized method. In the numerical section, we show that the proposed regularization method and training scheme yields an improvement on commonly used data sets, as compared to previously proposed heuristics.

AB - We consider the over-fitting problem for multinomial probabilistic Latent Semantic Analysis (pLSA) in collaborative filtering, using a regularization approach. For big data applications, the computational complexity is at a premium and we, therefore, consider a maximum a posteriori approach based on conjugate priors that ensure that complexity of each step remains the same as compared to the un-regularized method. In the numerical section, we show that the proposed regularization method and training scheme yields an improvement on commonly used data sets, as compared to previously proposed heuristics.

KW - Collaborative filtering

KW - Conjugate prior regularization

KW - Probabilistic latent semantic analysis

KW - Recommender systems

U2 - 10.23919/EUSIPCO.2017.8081661

DO - 10.23919/EUSIPCO.2017.8081661

M3 - Paper in conference proceeding

AN - SCOPUS:85041483446

VL - 2017-January

SP - 2501

EP - 2505

BT - 25th European Signal Processing Conference, EUSIPCO 2017

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 25th European Signal Processing Conference, EUSIPCO 2017

Y2 - 28 August 2017 through 2 September 2017

ER -

Conjugate-prior-regularized multinomial pLSA for collaborative filtering

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Cite this