Preference Relation-based Markov Random Fields for Recommender Systems

Shaowu Liu, Gang Li, Truyen Tran, Yuan Jiang
Asian Conference on Machine Learning, PMLR 45:157-172, 2016.

Abstract

A \emphpreference relation-based Top-N recommendation approach, \emphPrefMRF, is proposed to capture both the second-order and the higher-order interactions among users and items. Traditionally Top-N recommendation was achieved by predicting the item ratings first, and then inferring the item rankings, based on the assumption of availability of \emphexplicit feedbacks such as ratings, and the assumption that optimizing the ratings is equivalent to optimizing the item rankings. Nevertheless, both assumptions are not always true in real world applications. The proposed \emphPrefMRF approach drops these assumptions by explicitly exploiting the preference relations, a more practical user feedback. Comparing to related work, the proposed \emphPrefMRF approach has the unique property of modeling both the second-order and the higher-order interactions among users and items. To the best of our knowledge, this is the first time both types of interactions have been captured in \emphpreference relation-based method. Experiment results on public datasets demonstrate that both types of interactions have been properly captured, and significantly improved Top-N recommendation performance has been achieved.

Cite this Paper

BibTeX
@InProceedings{pmlr-v45-Liu15, title = {Preference Relation-based Markov Random Fields for Recommender Systems}, author = {Liu, Shaowu and Li, Gang and Tran, Truyen and Jiang, Yuan}, booktitle = {Asian Conference on Machine Learning}, pages = {157--172}, year = {2016}, editor = {Holmes, Geoffrey and Liu, Tie-Yan}, volume = {45}, series = {Proceedings of Machine Learning Research}, address = {Hong Kong}, month = {20--22 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v45/Liu15.pdf}, url = {https://proceedings.mlr.press/v45/Liu15.html}, abstract = {A \emphpreference relation-based Top-N recommendation approach, \emphPrefMRF, is proposed to capture both the second-order and the higher-order interactions among users and items. Traditionally Top-N recommendation was achieved by predicting the item ratings first, and then inferring the item rankings, based on the assumption of availability of \emphexplicit feedbacks such as ratings, and the assumption that optimizing the ratings is equivalent to optimizing the item rankings. Nevertheless, both assumptions are not always true in real world applications. The proposed \emphPrefMRF approach drops these assumptions by explicitly exploiting the preference relations, a more practical user feedback. Comparing to related work, the proposed \emphPrefMRF approach has the unique property of modeling both the second-order and the higher-order interactions among users and items. To the best of our knowledge, this is the first time both types of interactions have been captured in \emphpreference relation-based method. Experiment results on public datasets demonstrate that both types of interactions have been properly captured, and significantly improved Top-N recommendation performance has been achieved.} }
Endnote
%0 Conference Paper %T Preference Relation-based Markov Random Fields for Recommender Systems %A Shaowu Liu %A Gang Li %A Truyen Tran %A Yuan Jiang %B Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Geoffrey Holmes %E Tie-Yan Liu %F pmlr-v45-Liu15 %I PMLR %P 157--172 %U https://proceedings.mlr.press/v45/Liu15.html %V 45 %X A \emphpreference relation-based Top-N recommendation approach, \emphPrefMRF, is proposed to capture both the second-order and the higher-order interactions among users and items. Traditionally Top-N recommendation was achieved by predicting the item ratings first, and then inferring the item rankings, based on the assumption of availability of \emphexplicit feedbacks such as ratings, and the assumption that optimizing the ratings is equivalent to optimizing the item rankings. Nevertheless, both assumptions are not always true in real world applications. The proposed \emphPrefMRF approach drops these assumptions by explicitly exploiting the preference relations, a more practical user feedback. Comparing to related work, the proposed \emphPrefMRF approach has the unique property of modeling both the second-order and the higher-order interactions among users and items. To the best of our knowledge, this is the first time both types of interactions have been captured in \emphpreference relation-based method. Experiment results on public datasets demonstrate that both types of interactions have been properly captured, and significantly improved Top-N recommendation performance has been achieved.
RIS
TY - CPAPER TI - Preference Relation-based Markov Random Fields for Recommender Systems AU - Shaowu Liu AU - Gang Li AU - Truyen Tran AU - Yuan Jiang BT - Asian Conference on Machine Learning DA - 2016/02/25 ED - Geoffrey Holmes ED - Tie-Yan Liu ID - pmlr-v45-Liu15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 45 SP - 157 EP - 172 L1 - http://proceedings.mlr.press/v45/Liu15.pdf UR - https://proceedings.mlr.press/v45/Liu15.html AB - A \emphpreference relation-based Top-N recommendation approach, \emphPrefMRF, is proposed to capture both the second-order and the higher-order interactions among users and items. Traditionally Top-N recommendation was achieved by predicting the item ratings first, and then inferring the item rankings, based on the assumption of availability of \emphexplicit feedbacks such as ratings, and the assumption that optimizing the ratings is equivalent to optimizing the item rankings. Nevertheless, both assumptions are not always true in real world applications. The proposed \emphPrefMRF approach drops these assumptions by explicitly exploiting the preference relations, a more practical user feedback. Comparing to related work, the proposed \emphPrefMRF approach has the unique property of modeling both the second-order and the higher-order interactions among users and items. To the best of our knowledge, this is the first time both types of interactions have been captured in \emphpreference relation-based method. Experiment results on public datasets demonstrate that both types of interactions have been properly captured, and significantly improved Top-N recommendation performance has been achieved. ER -
APA
Liu, S., Li, G., Tran, T. & Jiang, Y.. (2016). Preference Relation-based Markov Random Fields for Recommender Systems. Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 45:157-172 Available from https://proceedings.mlr.press/v45/Liu15.html.

Related Material