Collaborative Filtering Using Associative Neural Memory

This paper introduces a collaborative filtering (CF) neural-network algorithm for recommending items. This algorithm connects the study of collaborative filtering with the study of associative memory, which is a neural network architecture that is significantly different from the dominant feedforward design. There are two types of CF systems – user-based and item-based, and we show that our CF system can have both interpretations. We further prove that, given a random subset of all users, our CF system is an unbiased estimator of predictions made from all users, thus theoretically justifying random sampling. We further apply standard neural network techniques, such as magnitude pruning and principle component analysis, to improve the system's scalability. Results from experiments with the MovieLens dataset are shown.

[1]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[2]  Pattie Maes,et al.  Social information filtering: algorithms for automating “word of mouth” , 1995, CHI '95.

[3]  Eric Horvitz,et al.  Collaborative Filtering by Personality Diagnosis: A Hybrid Memory and Model-Based Approach , 2000, UAI.

[4]  Mohamad H. Hassoun,et al.  Associative neural memories , 1993 .

[5]  Thomas Hofmann,et al.  Latent Class Models for Collaborative Filtering , 1999, IJCAI.

[6]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[7]  John Riedl,et al.  Analysis of recommendation algorithms for e-commerce , 2000, EC '00.

[8]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[9]  John Riedl,et al.  Item-based collaborative filtering recommendation algorithms , 2001, WWW '01.

[10]  Kenneth Y. Goldberg,et al.  Eigentaste: A Constant Time Collaborative Filtering Algorithm , 2001, Information Retrieval.

[11]  Chuck Lam,et al.  SNACK: incorporating social network information in automated collaborative filtering , 2004, EC '04.

[12]  Michael J. Pazzani,et al.  Learning Collaborative Information Filters , 1998, ICML.

[13]  John Riedl,et al.  Application of Dimensionality Reduction in Recommender System - A Case Study , 2000 .

[14]  John Riedl,et al.  An algorithmic framework for performing collaborative filtering , 1999, SIGIR '99.

[15]  Mohamad H. Hassoun,et al.  Associative neural memories , 1993 .

[16]  George Karypis,et al.  Evaluation of Item-Based Top-N Recommendation Algorithms , 2001, CIKM '01.

[17]  Andrew McCallum,et al.  Efficient clustering of high-dimensional data sets with application to reference matching , 2000, KDD '00.

[18]  Teuvo Kohonen,et al.  Correlation Matrix Memories , 1972, IEEE Transactions on Computers.

[19]  David Heckerman,et al.  Empirical Analysis of Predictive Algorithms for Collaborative Filtering , 1998, UAI.

[20]  J. Rice.  Mathematical Statistics and Data Analysis , 1988 .

[21]  David G. Stork,et al.  Pattern Classification , 1973 .

[22]  Craig Boutilier,et al.  Active Collaborative Filtering , 2002, UAI.