Collaborative Filtering via Rating Concentration

Bert Huang, Tony Jebara
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:334-341, 2010.

Abstract

While most popular collaborative filtering methods use low-rank matrix factorization and parametric density assumptions, this article proposes an approach based on distribution-free concentration inequalities. Using agnostic hierarchical sampling assumptions, functions of observed ratings are provably close to their expectations over query ratings, on average. A joint probability distribution over queries of interest is estimated using maximum entropy regularization. The distribution resides in a convex hull of allowable candidate distributions which satisfy concentration inequalities that stem from the sampling assumptions. The method accurately estimates rating distributions on synthetic and real data and is competitive with low rank and parametric methods which make more aggressive assumptions about the problem.

Cite this Paper


BibTeX
@InProceedings{pmlr-v9-huang10a, title = {Collaborative Filtering via Rating Concentration}, author = {Huang, Bert and Jebara, Tony}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {334--341}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/huang10a/huang10a.pdf}, url = {https://proceedings.mlr.press/v9/huang10a.html}, abstract = {While most popular collaborative filtering methods use low-rank matrix factorization and parametric density assumptions, this article proposes an approach based on distribution-free concentration inequalities. Using agnostic hierarchical sampling assumptions, functions of observed ratings are provably close to their expectations over query ratings, on average. A joint probability distribution over queries of interest is estimated using maximum entropy regularization. The distribution resides in a convex hull of allowable candidate distributions which satisfy concentration inequalities that stem from the sampling assumptions. The method accurately estimates rating distributions on synthetic and real data and is competitive with low rank and parametric methods which make more aggressive assumptions about the problem.} }
Endnote
%0 Conference Paper %T Collaborative Filtering via Rating Concentration %A Bert Huang %A Tony Jebara %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-huang10a %I PMLR %P 334--341 %U https://proceedings.mlr.press/v9/huang10a.html %V 9 %X While most popular collaborative filtering methods use low-rank matrix factorization and parametric density assumptions, this article proposes an approach based on distribution-free concentration inequalities. Using agnostic hierarchical sampling assumptions, functions of observed ratings are provably close to their expectations over query ratings, on average. A joint probability distribution over queries of interest is estimated using maximum entropy regularization. The distribution resides in a convex hull of allowable candidate distributions which satisfy concentration inequalities that stem from the sampling assumptions. The method accurately estimates rating distributions on synthetic and real data and is competitive with low rank and parametric methods which make more aggressive assumptions about the problem.
RIS
TY - CPAPER TI - Collaborative Filtering via Rating Concentration AU - Bert Huang AU - Tony Jebara BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-huang10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 334 EP - 341 L1 - http://proceedings.mlr.press/v9/huang10a/huang10a.pdf UR - https://proceedings.mlr.press/v9/huang10a.html AB - While most popular collaborative filtering methods use low-rank matrix factorization and parametric density assumptions, this article proposes an approach based on distribution-free concentration inequalities. Using agnostic hierarchical sampling assumptions, functions of observed ratings are provably close to their expectations over query ratings, on average. A joint probability distribution over queries of interest is estimated using maximum entropy regularization. The distribution resides in a convex hull of allowable candidate distributions which satisfy concentration inequalities that stem from the sampling assumptions. The method accurately estimates rating distributions on synthetic and real data and is competitive with low rank and parametric methods which make more aggressive assumptions about the problem. ER -
APA
Huang, B. & Jebara, T.. (2010). Collaborative Filtering via Rating Concentration. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:334-341 Available from https://proceedings.mlr.press/v9/huang10a.html.

Related Material