Distributed collaborative filtering with domain specialization
Published 19 October 2007
Shlomo Berkovsky, Tsvi Kuflik, Francesco Ricci⋆
Citations68
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The evaluation demonstrates that the aggregation improves the accuracy of a centralized system containing the same ratings and proves the feasibility and advantages of a distributed collaborative filtering scenario.
Abstract
User data scarcity has always been indicated among the major problems of collaborative filtering recommender systems. That is, if two users do not share sufficiently large set of items for whom their ratings are known, then the user-to-user similarity computation is not reliable and a rating prediction for one user can not be based on the ratings of the other. This paper shows that this problem can be solved, and that the accuracy of collaborative recommendations can be improved by: a) partitioning the collaborative user data into specialized and distributed repositories, and b) aggregating information coming from these repositories. This paper explores a content-dependent partitioning of collaborative movie ratings, where the ratings are partitioned according to the genre of the movie and presents an evaluation of four aggregation approaches. The evaluation demonstrates that the aggregation improves the accuracy of a centralized system containing the same ratings and proves the feasibility and advantages of a distributed collaborative filtering scenario.
Keywords
Computer ScienceDecision Sciences
IEEE Transactions on Knowledge and Data EngineeringToward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
10,115 Citations2005Gediminas Adomavičius, Alexander Tuzhilin
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches.
Item-based collaborative filtering recommendation algorithms
9,017 Citations2001Badrul Sarwar, George Karypis +2 more
This paper analyzes item-based collaborative ltering techniques and suggests that item- based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.
Artificial IntelligenceWrappers for feature subset selection
8,925 Citations1997Ron Kohavi, George H. John
The wrapper method searches for an optimal feature subset tailored to a particular algorithm and a domain and compares the wrapper approach to induction without feature subset selection and to Relief, a filter approach tofeature subset selection.
ACM Transactions on Information SystemsEvaluating collaborative filtering recommender systems
5,762 Citations2004Jonathan L. Herlocker, Joseph A. Konstan +2 more
The key decisions in evaluating collaborative filtering recommender systems are reviewed: the user tasks being evaluated, the types of analysis and datasets being used, the ways in which prediction quality is measured, the evaluation of prediction attributes other than quality, and the user-based evaluation of the system as a whole.
IEEE Internet ComputingAmazon.com recommendations: item-to-item collaborative filtering
5,369 Citations2003Greg Linden, Brent Smith +1 more
This work compares three common approaches to solving the recommendation problem: traditional collaborative filtering, cluster models, and search-based methods, and their algorithm, which is called item-to-item collaborative filtering.
User Modeling and User-Adapted InteractionHybrid Recommender Systems: Survey and Experiments
3,764 Citations2002Robin Burke
This paper surveys the landscape of actual and possible hybrid recommenders, and introduces a novel hybrid, EntreeC, a system that combines knowledge-based recommendation and collaborative filtering to recommend restaurants, and shows that semantic ratings obtained from the knowledge- based part of the system enhance the effectiveness of collaborative filtering.
ACM SIGIR ForumAn Algorithmic Framework for Performing Collaborative Filtering
2,552 Citations2017Jonathan L. Herlocker, Joseph A. Konstan +2 more
An algorithmic framework for performing collaborative filtering
1,973 Citations1999Jonathan L. Herlocker, Joseph A. Konstan +2 more
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage.
Data Mining and Knowledge DiscoveryE-Commerce Recommendation Applications
1,518 Citations2001J. Ben Schafer, Joseph A. Konstan +1 more
An explanation of how recommender systems are related to some traditional database analysis techniques is presented, and a taxonomy ofRecommender systems is created, including the inputs required from the consumers, the additional knowledge required from a database, the ways the recommendations are presented to consumers,The technologies used to create the recommendations, and the level of personalization of the recommendations.
Introduction to Modern Information Retrieval
921 Citations1999Gobinda Chowdhury
It is this book's contention that it also benefits information professionals to learn the theory, techniques and tools that constitute the traditional approaches to the organization and processing of information.
ACM Transactions on Information SystemsPocketLens
322 Citations2004Brad Miller, Joseph A. Konstan +1 more
The new PocketLens collaborative filtering algorithm along with five peer-to-peer architectures for finding neighbors are presented and evaluated in a series of offline experiments, showing that Pocketlens can run on connected servers, on usually connected workstations, or on occasionally connected portable devices, and produce recommendations that are as good as the best published algorithms to date.
An automatic weighting scheme for collaborative filtering
292 Citations2004Rong Jin, Joyce Chai +1 more
An optimization algorithm to automatically compute the weights for different items based on their ratings from training users will create a clustered distribution for user vectors in the item space by bringing users of similar interests closer and separating users of different interests more distant.
Social Choice Theory and Recommender Systems: Analysis of the Axiomatic Foundations of Collaborative Filtering
192 Citations2000David M. Pennock, Eric Horvitz +1 more
Internet Reference Services QuarterlyThe Internet Movie Database
162 Citations2001Cherié L. Weible
The Internet resource of the Internet Movie Database is explored and its potential benefits for librarians are explored.
Lecture notes in computer scienceCross-Domain Mediation in Collaborative Filtering
153 Citations2007Shlomo Berkovsky, Tsvi Kuflik +1 more
The paper presents several mediation approaches and initial experimental evaluation demonstrating that the mediation can improve the accuracy of the generated predictions.
Knowledge and Information SystemsFeature Weighting and Instance Selection for Collaborative Filtering: An Information-Theoretic Approach*
77 Citations2003Kai Yu, Xiaowei Xu +2 more
A unified information-theoretic approach to measure the relevance of features and instances in collaborative filtering is presented and feature weighting and instance selection methods are proposed for collaborative filtering.
Similarity measure and instance selection for collaborative filtering
52 Citations2003Chun Zeng, Chunxiao Xing +1 more
This paper adopts two techniques: a matrix conversion method for similarity measure and an instance selection method and presents an improved collaborative filtering algorithm based on these two methods that shows its satisfactory accuracy and performance.
Lecture notes in computer scienceWays of Computing Diverse Collaborative Recommendations
35 Citations2006Derek Bridge, John P. Kelly
This work devise and compare four different mechanisms for enhancing the diversity of the recommendations made by collaborative recommenders and finds that measuring the distance between products using Hamming Distance is more effective than using Inverse Pearson Correlation.
Lecture notes in computer scienceDecentralized Mediation of User Models for a Better Personalization
24 Citations2006Shlomo Berkovsky
The details of a decentralized mediator for cross-domain and cross-technique translation and aggregation of partial UMs for enriching UMs managed by personalization services and improving the quality of the provided personalization are discussed.
Collaborative filtering over distributed environment
10 Citations2005Shlomo Berkovsky, Paolo Busetta +3 more
This work proposes a novel approach to overcome the inherent limitations of CF (sparsity of data and cold start) by exploiting multiple distributed information repositories by exploitingMultiple distributed information repository may belong to a single domain or to different domains.
Identifying Inter-Domain Similarities through Content-Based Analysis of Hierarchical Web-Directories
6 Citations2006Shlomo Berkovsky, Dan Goldwasser +2 more
This paper proposes to compute inter-domain similarities by exploiting well-known Information Retrieval techniques for comparing textual contents of the Web-sites, classified under the domain nodes in Web-directories.