Information Services]: Web-based services

Citations in the corpus

• Improved Recurrent Neural Networks for Session-based Recommendations (2016, methodology): “One way to solve this cold-start problem is to use pairwise preference regression [20].”
• Facing the cold start problem in recommender systems (2014, background): “In this paper, we present a method to alleviate the new user cold start problem for RSs applying CF.”
• Generalizing to Unseen Entities and Entity Pairs with Row-less Universal Schema (2016, methodology): “Riedel et al. (2010) used a relaxation of distant supervision training where all sentences for an entity pair (bag) are considered jointly and only the most relevant sentence is treated as the single training example for the bag’s label.”
• A collaborative filtering approach to mitigate the new user cold start problem (2012, background): “The new item problem [38,39] arises due to the fact that the new items entered in RS do not usually have initial votes, and therefore, they are not likely to be recommended.”
• Recommender systems survey (2013, background): “The new item problem [174,172] arises because the new items entered in RS do not usually have initial ratings, and therefore, they are not likely to be recommended.”
• Functional matrix factorizations for cold-start recommendation (2011, background): “The content features can be used to capture the similarities between users and items and thus reduce the amount of data required to make accurate predictions [2,3,10,15,23,25].”
• MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation (2019, methodology): “From the performance degradation, we could infer that the performance gaps of PPR between the non-cold-start scenario and cold-start scenarios come from the overfitting when sparsity is low.”
• Cold-start Active Learning with Robust Ordinal Matrix Factorization (2014, background): “Copyright 2014 by the author(s). mographic information) to improve predictive performance (Claypool et al., 1999; Park et al., 2006; Ahn, 2008; Park & Chu, 2009).”
• Inferring Networks of Substitutable and Complementary Products (2015, background): “Although it is promising that we are able to recommend substitutes and complements from the text of product reviews, an obvious question remains as to what can be done for new products, that do not yet have any reviews associated with them, known as the ‘cold-start’ problem in recommender systems [1”
• LARA: Attribute-to-feature Adversarial Learning for New-item Recommendation (2020, background): “Park et al. [24] gave another solution to utilize items’ attribute information.”
• Alors: An algorithm recommender system (2017, unknown): “When it is the case, CF successfully handles the so-called cold-start task (Ahn, 2008; Park and Chu, 2009; Liu et al., 2014): emitting recommendations for a brand new user or selecting algorithms for a brand new problem instance.”
• Learning Attribute-to-Feature Mappings for Cold-Start Recommendations (2010, methodology): “For the experiments, we use the MovieLens 1M dataset 2 , which is a commonly-used rating dataset [10], [ 18 ].”
• A Review of Challenges and Opportunities in Machine Learning for Health. (2018, methodology): “This relates to the ideas from “ N=1 ” crossover studies in experimental design 72 .”
• Current challenges and visions in music recommender systems research (2017, methodology): “e recommendations. „is metric has originally been proposed to evaluate e‡ectiveness of information retrieval systems [94]. It is nowadays also frequently used for evaluating music recommender systems [120, 139, 185]. Assuming that the recommendations for user u are sorted according to the predicted ”