Transfer learning for collaborative filtering via a rating-matrix generative model

By Bin Li, Qiang Yang, Xiangyang Xue. 2009

385 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

Citations in the corpus

Cross-Domain Recommender Systems (2015, background): “…al. 2014 [44] books, games, music, movies & TV shows ratings Winoto & Tang 2008 [66] item books, movies ratings - BookCrossing, MovieLens/EachMovie Li et al. 2009 [40] [41] Gao et al. 2013 [26] ratings, tags - LibraryThing, MovieLens Zhang et al. 2010 [67] Shi et al. 2011 [59] Enrich et al. 2013…”
Adaptation Regularization: A General Framework for Transfer Learning (2014, background): “, text categorization [2], [3], sentiment analysis [4], [5], image classification [6] and retrieval [7], video summarization [8], and collaborative recommendation [9].”
Nonparametric bayesian multitask collaborative filtering (2013, methodology): “In addition, an older related approach presented in [17] proposed a rating-matrix generative model to perform multitask collaborative filtering.”
Cross-Domain Recommendation via Cluster-Level Latent Factor Model (2013, methodology): “Following [2] we randomly choose 500 users with more than 16 ratings and 1000 movies for experiments.”
Feature-based transfer learning with real-world applications (2010, background): “Web applications of transfer learning include text classification across domains [151, 47, 48, 72, 195, 207, 36, 204, 213, 203], advertising [40, 39], learn to rank across domains [10, 192, 35, 68] and multi-domain collaborative filtering [103, 102, 29, 223, 143].”
Transfer learning in heterogeneous collaborative filtering domains (2013, methodology): “codebook sharing methods of CBT [31] and RMGM [32] can be considered as adaptive and collective extensions of [50,19].”
Artificial intelligence in recommender systems (2020, methodology): “A probabilistic model named rating matrix generated model (RMGM) was extended from CBT which relaxes the hard group membership to soft membership [116].”
Personalized recommendation via cross-domain triadic factorization (2013, background): “Rating-Matrix Generative Model [13] extends this idea with a probabilistic model to solve collective transfer learning problems.”
Cross-Domain Recommendation: An Embedding and Mapping Approach (2017, background): “The first type works in an asymmetric way, aiming to leverage data in an auxiliary domain to alleviate data sparsity of the target domain [Li et al., 2009a; 2009b; Pan et al., 2010].”
A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems (2015, background): “In [12], the authors studied the cross domain recommendation in the case where there existed no shared users or items be-tween domains.”
A Deep Framework for Cross-Domain and Cross-System Recommendations (2018, background): “In addition to transferring latent factors, transferring rating patterns [ Li et al. , 2009 ] becomes effective in transfer-based approaches.”
Collaborative Filtering beyond the User-Item Matrix (2014, methodology): “Codebook transfer (CBT) [Li et al. 2009a] and the rating-matrix generative model (RMGM) [Li et al. 2009b] are two approaches that transfer the knowledge from an auxiliary domain by learning an implicit clusterlevel rating pattern that can be shared with a target domain.”
Web Data Extraction, Applications and Techniques: A Survey (2012, methodology): “For instance, some approaches use co-clustering [80], other clustering techniques in conjunction with probabilistic models [81] and, finally, other approaches project the user and item space in the various domains in a shared latent space by means of regularization techniques [129].”
Transfer Learning in Collaborative Filtering for Sparsity Reduction (2010, neutral): “Also, CBT and RMGM can neither make use of user side nor item side shared information, and only take a general explicit rating matrix as its auxiliary input.”