Categories and Subject Descriptors

By Andrew I. Schein, Alexandrin Popescul, Lyle Ungar, David M. Pennock. 2001

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback (2015, background): “Although a variety of sources of data have been used to build hybrid models to make cold start or context-aware recommendations (Schein et al. 2002), from text (Bao, Fang, and Zhang 2014), to a user’s physical location (Qiao et al.”
Image-Based Recommendations on Styles and Substitutes (2015, background): “Creating a labeled dataset is particularly onerous when modeling pairwise distances because the number of annotations required scales with the square of the number of elements.”
Ask the GRU: Multi-task Learning for Deep Text Recommendations (2016, methodology): “Such methods can make recommendations for new items but are limited in their performance since they cannot employ similarity between user preferences [5, 10, 11].”
Joint Deep Modeling of Users and Items Using Reviews for Recommendation (2017, background): “The cold start problem [27] is prevalent in recommender systems.”
Regression-based latent factor models (2009, background): “[25] extends aspect model to combine item content and user ratings under a single probabilistic framework.”
A Survey of Collaborative Filtering Techniques (2009, methodology): “But in actual situations, ROC curves may intersect with each other.”
A unified approach to building hybrid recommender systems (2009, methodology): “The use of aspect models [30] has been proposed as an approach to recommendation that is robust in the face of the item cold-start problem.”
Factorization Bandits for Interactive Recommendation (2017, unknown): “The classical offline training and online testing paradigm for factorization models becomes incompetent to handle the dynamics of users' preferences, known as cold-start (Schein et al. 2002).”
Combining content-based and collaborative recommendations: A hybrid approach based on Bayesian networks (2010, background): “Independently of the technique used and based on how the recommendations are made, recommender systems are usually classified [3] into the following categories: Collaborative filtering systems that attempt to identify groups of people with similar tastes to those of the user and recommend items that”
Learning multiple-question decision trees for cold-start recommendation (2013, background): “To copy therwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.”
Multiple domain user personalization (2011, methodology): “feature based methods have been developed that performs well [13, 17].”
You are what you like! Information leakage through users' Interests (2012, background): “In particular, collaborative filtering suffers from a “coldstart” effect [24], which means that the system cannot draw correct inferences for users who have insufficient information (i.”
DDTCDR: Deep Dual Transfer Cross Domain Recommendation (2019, background): “However, these models suffer the cold start and the data sparsity problems [1, 28], for we”
Comparison of collaborative filtering algorithms (2011, unknown): “— Cold-start [Schein et al. 2002].”
Transferable Contextual Bandit for Cross-Domain Recommendation (2018, background): “The exploitationexploration dilemma and the cold-start problem are two major obstacles to the successful deployment of a RecSys (Schein et al. 2002; Li et al. 2010).”
A Comprehensive Survey of Neighborhood-based Recommendation Methods (2011, background): “This is aggravated by the fact that users or items newly added to the system may have no ratings at all, a problem known as cold-start [69].”
Learning Hidden Features for Contextual Bandits (2016, background): “Another unique advantage of hLinUCB that is worth our attention is its ability to address cold-start, a serious challenge in online recommendation [21].”