George
0 likes185 views
This document summarizes recent work on improving top-N recommender systems using item-based neighborhood methods. It describes two approaches: 1) estimating a sparse item-item similarity matrix directly from training data using structural equation modeling, and 2) extending this framework to estimate a factored item-item similarity matrix to handle sparse datasets. It also discusses incorporating item side information to improve recommendations and address cold-start problems.
George
- 1. Top-N Recommender Systems: Revisiting Item Neighborhood Methods George Karypis Department of Computer Science & Engineering University of Minnesota karypis@cs.umn.edu http://www.cs.umn.edu/~karypis Abstract Top-N recommender systems are designed to generate a ranked list of items that a user will find useful based on the user’s prior activity. These systems have become ubiquitous and are an essential tool for information filtering and (e-)commerce. Over the years, collaborative filtering, which derive these recommendations by leveraging past activities of groups of users, has emerged as the most prominent approach for solving this problem. Among the multitude of methods that have been developed, item-based nearest neighbor algorithms are among the simplest and yet best-performing methods for Top-N recommender systems. These methods rank the items to be recommended based on how similar they are to the items in a user’s prior activity history, using various co-occurrence similarity measures. In this talk we present our recent work in these item-based neighborhood methods that has substantially improved the accuracy of the predictions. One shortcoming of traditional item- based neighborhood methods is that they rely on a similarity measure that needs to be specified a priori. To address this problem we developed a class of item-based neighborhood methods that directly estimate from the training data a sparse item-item similarity matrix. This similarity matrix is estimated using a structural equation modeling (SEM) framework, which requires each column of the user-item matrix to be approximated as a sparse aggregation of some other columns. These other columns correspond to the learned neighbors and their aggregation weights to the learned similarities. A second shortcoming of item-based neighborhood methods is that the item-item similarity measures rely on co-occurrences, which become problematic when the datasets are very sparse and the number of items pairs with sufficiently many co- occurrences is small. To address this problem we extended the SEM framework to estimate a factored version of the item-item similarity matrix. This factored representation projects the items in a lower dimensional space, which allows for meaningful similarity estimates between items that never co-occurred in the original user-item matrix. In addition to the above, we also discuss and present result from our work to enhance the above SEM-models by incorporating item side information to further improve the Top-N recommendation accuracy and to also address the item cold-start recommendation problem. Bio George Karypis is a professor at the Department of Computer Science & Engineering at the University of Minnesota, Twin Cities. His research interests spans the areas of data mining, bioinformatics, cheminformatics, high performance computing, information retrieval, collaborative filtering, and scientific computing. His research has resulted in the development of software libraries for serial and parallel graph partitioning (METIS and ParMETIS), hypergraph partitioning (hMETIS), for parallel Cholesky factorization (PSPASES), for collaborative filtering- based recommendation algorithms (SUGGEST), clustering high dimensional datasets (CLUTO), finding frequent patterns in diverse datasets (PAFI), and for protein secondary structure prediction (YASSPP). He has coauthored over 200 papers on these topics and a book title “Introduction to Parallel Computing” (Publ. Addison Wesley, 2003, 2nd edition). In addition, he is
- 2. serving on the program committees of many conferences and workshops on these topics, and on the editorial boards of the IEEE Transactions on Knowledge and Data Engineering, Social Network Analysis and Data Mining Journal, International Journal of Data Mining and Bioinformatics, the journal on Current Proteomics, Advances in Bioinformatics, and Biomedicine and Biotechnology.