A Coupled Indian Buffet Process Model for Collaborative Filtering

Sotirios P. Chatzis
Proceedings of the Asian Conference on Machine Learning, PMLR 25:65-79, 2012.

Abstract

The dramatic rates new digital content becomes available has brought collaborative filtering systems in the epicenter of computer science research in the last decade. In this paper, we propose a novel methodology for rating prediction utilizing concepts from the field of Bayesian nonparametrics. The basic concept that underlies our approach is that each user rates a presented item based on the latent genres of the item and the latent interests of the user. Each item may belong to more than one genre, and each user may belong to more than one latent interest class. The number of existing latent genres and interests are not known beforehand, but should be inferred in a data-driven fashion. We devise a novel hierarchical factor analysis model to formulate our approach under these assumptions. We impose suitable priors over the allocation of items into genres, and users into interests; specifically, we utilize a novel scheme which comprises two coupled Indian buffet process priors that allow the number of latent classes (genres/interests) to be automatically inferred. We experiment on a large set of real ratings data, and show that our approach outperforms four common baselines, including two very competitive state-of-the-art approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v25-chatzis12, title = {A Coupled Indian Buffet Process Model for Collaborative Filtering}, author = {Chatzis, Sotirios P.}, booktitle = {Proceedings of the Asian Conference on Machine Learning}, pages = {65--79}, year = {2012}, editor = {Hoi, Steven C. H. and Buntine, Wray}, volume = {25}, series = {Proceedings of Machine Learning Research}, address = {Singapore Management University, Singapore}, month = {04--06 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v25/chatzis12/chatzis12.pdf}, url = {https://proceedings.mlr.press/v25/chatzis12.html}, abstract = {The dramatic rates new digital content becomes available has brought collaborative filtering systems in the epicenter of computer science research in the last decade. In this paper, we propose a novel methodology for rating prediction utilizing concepts from the field of Bayesian nonparametrics. The basic concept that underlies our approach is that each user rates a presented item based on the latent genres of the item and the latent interests of the user. Each item may belong to more than one genre, and each user may belong to more than one latent interest class. The number of existing latent genres and interests are not known beforehand, but should be inferred in a data-driven fashion. We devise a novel hierarchical factor analysis model to formulate our approach under these assumptions. We impose suitable priors over the allocation of items into genres, and users into interests; specifically, we utilize a novel scheme which comprises two coupled Indian buffet process priors that allow the number of latent classes (genres/interests) to be automatically inferred. We experiment on a large set of real ratings data, and show that our approach outperforms four common baselines, including two very competitive state-of-the-art approaches.} }
Endnote
%0 Conference Paper %T A Coupled Indian Buffet Process Model for Collaborative Filtering %A Sotirios P. Chatzis %B Proceedings of the Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2012 %E Steven C. H. Hoi %E Wray Buntine %F pmlr-v25-chatzis12 %I PMLR %P 65--79 %U https://proceedings.mlr.press/v25/chatzis12.html %V 25 %X The dramatic rates new digital content becomes available has brought collaborative filtering systems in the epicenter of computer science research in the last decade. In this paper, we propose a novel methodology for rating prediction utilizing concepts from the field of Bayesian nonparametrics. The basic concept that underlies our approach is that each user rates a presented item based on the latent genres of the item and the latent interests of the user. Each item may belong to more than one genre, and each user may belong to more than one latent interest class. The number of existing latent genres and interests are not known beforehand, but should be inferred in a data-driven fashion. We devise a novel hierarchical factor analysis model to formulate our approach under these assumptions. We impose suitable priors over the allocation of items into genres, and users into interests; specifically, we utilize a novel scheme which comprises two coupled Indian buffet process priors that allow the number of latent classes (genres/interests) to be automatically inferred. We experiment on a large set of real ratings data, and show that our approach outperforms four common baselines, including two very competitive state-of-the-art approaches.
RIS
TY - CPAPER TI - A Coupled Indian Buffet Process Model for Collaborative Filtering AU - Sotirios P. Chatzis BT - Proceedings of the Asian Conference on Machine Learning DA - 2012/11/17 ED - Steven C. H. Hoi ED - Wray Buntine ID - pmlr-v25-chatzis12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 25 SP - 65 EP - 79 L1 - http://proceedings.mlr.press/v25/chatzis12/chatzis12.pdf UR - https://proceedings.mlr.press/v25/chatzis12.html AB - The dramatic rates new digital content becomes available has brought collaborative filtering systems in the epicenter of computer science research in the last decade. In this paper, we propose a novel methodology for rating prediction utilizing concepts from the field of Bayesian nonparametrics. The basic concept that underlies our approach is that each user rates a presented item based on the latent genres of the item and the latent interests of the user. Each item may belong to more than one genre, and each user may belong to more than one latent interest class. The number of existing latent genres and interests are not known beforehand, but should be inferred in a data-driven fashion. We devise a novel hierarchical factor analysis model to formulate our approach under these assumptions. We impose suitable priors over the allocation of items into genres, and users into interests; specifically, we utilize a novel scheme which comprises two coupled Indian buffet process priors that allow the number of latent classes (genres/interests) to be automatically inferred. We experiment on a large set of real ratings data, and show that our approach outperforms four common baselines, including two very competitive state-of-the-art approaches. ER -
APA
Chatzis, S.P.. (2012). A Coupled Indian Buffet Process Model for Collaborative Filtering. Proceedings of the Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 25:65-79 Available from https://proceedings.mlr.press/v25/chatzis12.html.

Related Material