fLDA: matrix factorization through latent dirichlet allocation

By Deepak K. Agarwal, Bee-Chung Chen. Web Search and Data Mining, 2010

304 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/bdb1d0bc054039b1c967a6d3fd1e1bf2abb1833c

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

TopicMF: Simultaneously Exploiting Ratings and Reviews for Recommendation (2014, methodology): “For example, fLDA (Agarwal and Chen 2010), extended from matrix factorization, regularizes both user and item factors in a supervised manner through explicit user features and the bag of words associated with each item.”
Learning Attribute-to-Feature Mappings for Cold-Start Recommendations (2010, methodology): “fLDA [ 2 ] uses content data for rating prediction.”
Recommender systems with social regularization (2011, methodology): “From the above definition, we can see that VSS similarity in Sim(i, f) is within the range [0, 1], and a larger value means users i and f are more similar.”
Collaborative topic modeling for recommending scientific articles (2011, methodology): “Among these, the closest work to ours is fLDA by [2].”
Relational Collaborative Topic Regression for Recommender Systems (2015, methodology): “Hybrid methods [2], [3], [6], [12], [15], [16], [17], [20], [32], [34], [40], [43], [47], [48] combine both content-based methods and CF based methods by ensemble techniques.”
Ratings meet reviews, a combined approach to recommend (2014, background): “Learning an interpretable model could help alleviate the cold-start problem [1, 13].”
Content-based recommendations with Poisson factorization (2014, methodology): “Agarwal and Chen [1] propose fLDA, a latent factor model which combines document features through their empirical LDA [2] topic intensities and other covariates, to predict user preferences.”
Artificial intelligence in recommender systems (2020, unknown): “Item metadata in “bag-of-words” representation are analyzed by topic models, which are integrated with matrix factorization methods to manage both cold-start and warm-start scenarios [184].”
Recommender Systems (2012, background): “It can be also extended to include general meta-data of users and objects [196].”
Collaborative Filtering beyond the User-Item Matrix (2014, background): “Collaborative Filtering beyond the User-Item Matrix 3:31 by allowing them to adjust the recommendations for this user [Chen and Pu 2012].”
Challenging the Long Tail Recommendation (2012, background): “• Matrix Factorization: Recently, several recommendation algorithms based onMatrix Factorization have been proposed [16, 2].”
Collaborative Metric Learning (2017, background): “This scheme penalizes a positive item at a lower rank much more heavily than one at the top, and produces the stateof-the-art results in many prior works [50, 53, 28].”
Coupled Matrix Factorization Within Non-IID Context (2014, background): “For example, many researchers try to influence or precisely estimate the latent factors [13] [6] [11] [1] [2] [19] through considering the attributes or topics information of users and items for latent factor models.”
Toward Implicit Sample Noise Modeling: Deviation-driven Matrix Factorization (2016, background): “Moreover, contrasting most conventional modeling for Gaussian likelihood with shared variance (Agarwal and Chen 2010; Mnih and Salakhutdinov 2007; Salakhutdinov and Mnih 2008), the deviation-driven modeling represents Gaussian likelihood in a per-instance variance manner.”
Novel Hybrid Integration Approach of Bagging-Based Fisher’s Linear Discriminant Function for Groundwater Potential Analysis (2019, unknown): “FLDA is one of the widespread feature recognition method in various fields (Agarwal and Chen 2010).”