A graphical model formulation of collaborative filtering neighbourhood methods with fast maximum entropy training
Date
2012
Authors
Defazio, Aaron
Caetano, Tiberio
Journal Title
Journal ISSN
Volume Title
Publisher
Conference Organising Committee
Abstract
Item neighbourhood methods for collaborative filtering learn a weighted graph over the set of items, where each item is connected to those it is most similar to. The prediction of a user's rating on an item is then given by that rating of neighbouring items, weighted by their similarity. This paper presents a new neighbourhood approach which we call item fields, whereby an undirected graphical model is formed over the item graph. The resulting prediction rule is a simple generalization of the classical approaches, which takes into account non-local information in the graph, allowing its best results to be obtained when using drastically fewer edges than other neighbourhood approaches. A fast approximate maximum entropy training method based on the Bethe approximation is presented, which uses a simple gradient ascent procedure. When using precomputed sufficient statistics on the Movielens datasets, our method is faster than maximum likelihood approaches by two orders of magnitude.
Description
Keywords
Keywords: Bethe approximation; Classical approach; Collaborative filtering; Data sets; Gradient ascent; GraphicaL model; Maximum entropy; Maximum likelihood approaches; Neighbourhood; Nonlocal; Orders of magnitude; Prediction rules; Sufficient statistics; Training
Citation
Collections
Source
Proceedings of the 29th International Conference on Machine Learning, ICML 2012
Type
Conference paper
Book Title
Entity type
Access Statement
License Rights
DOI
Restricted until
2037-12-31