Ordinal Random Fields for Recommender Systems

Shaowu Liu, Truyen Tran, Gang Li
Proceedings of the Sixth Asian Conference on Machine Learning, PMLR 39:283-298, 2015.

Abstract

Recommender Systems heavily rely on numerical preferences, whereas the importance of ordinal preferences has only been recognised in recent works of Ordinal Matrix Factorisation (OMF). Although the OMF can effectively exploit ordinal properties, it captures only the higher-order interactions among users and items, without considering the localised interactions properly. This paper employs Markov Random Fields (MRF) to investigate the localised interactions, and proposes a unified model called Ordinal Random Fields (ORF) to take advantages of both the representational power of the MRF and the ease of modelling ordinal preferences by the OMF. Experimental result on public datasets demonstrates that the proposed ORF model can capture both types of interactions, resulting in improved recommendation accuracy.

Cite this Paper

BibTeX
@InProceedings{pmlr-v39-liu14, title = {Ordinal Random Fields for Recommender Systems}, author = {Liu, Shaowu and Tran, Truyen and Li, Gang}, booktitle = {Proceedings of the Sixth Asian Conference on Machine Learning}, pages = {283--298}, year = {2015}, editor = {Phung, Dinh and Li, Hang}, volume = {39}, series = {Proceedings of Machine Learning Research}, address = {Nha Trang City, Vietnam}, month = {26--28 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v39/liu14.pdf}, url = {https://proceedings.mlr.press/v39/liu14.html}, abstract = {Recommender Systems heavily rely on numerical preferences, whereas the importance of ordinal preferences has only been recognised in recent works of Ordinal Matrix Factorisation (OMF). Although the OMF can effectively exploit ordinal properties, it captures only the higher-order interactions among users and items, without considering the localised interactions properly. This paper employs Markov Random Fields (MRF) to investigate the localised interactions, and proposes a unified model called Ordinal Random Fields (ORF) to take advantages of both the representational power of the MRF and the ease of modelling ordinal preferences by the OMF. Experimental result on public datasets demonstrates that the proposed ORF model can capture both types of interactions, resulting in improved recommendation accuracy.} }
Endnote
%0 Conference Paper %T Ordinal Random Fields for Recommender Systems %A Shaowu Liu %A Truyen Tran %A Gang Li %B Proceedings of the Sixth Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2015 %E Dinh Phung %E Hang Li %F pmlr-v39-liu14 %I PMLR %P 283--298 %U https://proceedings.mlr.press/v39/liu14.html %V 39 %X Recommender Systems heavily rely on numerical preferences, whereas the importance of ordinal preferences has only been recognised in recent works of Ordinal Matrix Factorisation (OMF). Although the OMF can effectively exploit ordinal properties, it captures only the higher-order interactions among users and items, without considering the localised interactions properly. This paper employs Markov Random Fields (MRF) to investigate the localised interactions, and proposes a unified model called Ordinal Random Fields (ORF) to take advantages of both the representational power of the MRF and the ease of modelling ordinal preferences by the OMF. Experimental result on public datasets demonstrates that the proposed ORF model can capture both types of interactions, resulting in improved recommendation accuracy.
RIS
TY - CPAPER TI - Ordinal Random Fields for Recommender Systems AU - Shaowu Liu AU - Truyen Tran AU - Gang Li BT - Proceedings of the Sixth Asian Conference on Machine Learning DA - 2015/02/16 ED - Dinh Phung ED - Hang Li ID - pmlr-v39-liu14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 39 SP - 283 EP - 298 L1 - http://proceedings.mlr.press/v39/liu14.pdf UR - https://proceedings.mlr.press/v39/liu14.html AB - Recommender Systems heavily rely on numerical preferences, whereas the importance of ordinal preferences has only been recognised in recent works of Ordinal Matrix Factorisation (OMF). Although the OMF can effectively exploit ordinal properties, it captures only the higher-order interactions among users and items, without considering the localised interactions properly. This paper employs Markov Random Fields (MRF) to investigate the localised interactions, and proposes a unified model called Ordinal Random Fields (ORF) to take advantages of both the representational power of the MRF and the ease of modelling ordinal preferences by the OMF. Experimental result on public datasets demonstrates that the proposed ORF model can capture both types of interactions, resulting in improved recommendation accuracy. ER -
APA
Liu, S., Tran, T. & Li, G.. (2015). Ordinal Random Fields for Recommender Systems. Proceedings of the Sixth Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 39:283-298 Available from https://proceedings.mlr.press/v39/liu14.html.

Related Material