An Active Approach to Collaborative Filtering

Richard S. Zemel, Craig Boutilier
Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, PMLR R4:330-337, 2003.

Abstract

Collaborative filtering allows the preferences of multiple users to be pooled in a principled way in order to make recommendations about products, services or information unseen by a specific user. We consider here the problem of online and interactive collaborative filtering: given the current ratings and recommendations associated with a user, what queries (new ratings) would most improve the quality of the recommendations made? This can be cast in a straightforward fashion in terms of expected value of information; but the online computational cost of computing optimal queries is prohibitive. We show how offline precomputation of bounds on value of information, and of prototypes in query space, can be used to dramatically reduce the required online computation. The framework we develop is quite general, but we derive detailed bounds for the multiplecause vector quantization model, and empirically demonstrate the value of our active approach using this model.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR4-zemel03a, title = {An Active Approach to Collaborative Filtering}, author = {Zemel, Richard S. and Boutilier, Craig}, booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics}, pages = {330--337}, year = {2003}, editor = {Bishop, Christopher M. and Frey, Brendan J.}, volume = {R4}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r4/zemel03a/zemel03a.pdf}, url = {https://proceedings.mlr.press/r4/zemel03a.html}, abstract = {Collaborative filtering allows the preferences of multiple users to be pooled in a principled way in order to make recommendations about products, services or information unseen by a specific user. We consider here the problem of online and interactive collaborative filtering: given the current ratings and recommendations associated with a user, what queries (new ratings) would most improve the quality of the recommendations made? This can be cast in a straightforward fashion in terms of expected value of information; but the online computational cost of computing optimal queries is prohibitive. We show how offline precomputation of bounds on value of information, and of prototypes in query space, can be used to dramatically reduce the required online computation. The framework we develop is quite general, but we derive detailed bounds for the multiplecause vector quantization model, and empirically demonstrate the value of our active approach using this model.}, note = {Reissued by PMLR on 01 April 2021.} }
Endnote
%0 Conference Paper %T An Active Approach to Collaborative Filtering %A Richard S. Zemel %A Craig Boutilier %B Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2003 %E Christopher M. Bishop %E Brendan J. Frey %F pmlr-vR4-zemel03a %I PMLR %P 330--337 %U https://proceedings.mlr.press/r4/zemel03a.html %V R4 %X Collaborative filtering allows the preferences of multiple users to be pooled in a principled way in order to make recommendations about products, services or information unseen by a specific user. We consider here the problem of online and interactive collaborative filtering: given the current ratings and recommendations associated with a user, what queries (new ratings) would most improve the quality of the recommendations made? This can be cast in a straightforward fashion in terms of expected value of information; but the online computational cost of computing optimal queries is prohibitive. We show how offline precomputation of bounds on value of information, and of prototypes in query space, can be used to dramatically reduce the required online computation. The framework we develop is quite general, but we derive detailed bounds for the multiplecause vector quantization model, and empirically demonstrate the value of our active approach using this model. %Z Reissued by PMLR on 01 April 2021.
APA
Zemel, R.S. & Boutilier, C.. (2003). An Active Approach to Collaborative Filtering. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R4:330-337 Available from https://proceedings.mlr.press/r4/zemel03a.html. Reissued by PMLR on 01 April 2021.

Related Material