Regression-based latent factor models

By Deepak K. Agarwal, Bee-Chung Chen. 2009

561 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics, Representation & Self-Supervised Learning

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

1. Xiangnan He
2. Julian McAuley
3. Qiang Yang
4. Xing Xie
5. Hao Wang
6. David M. Blei
7. Tat-seng Chua
8. Yoshua Bengio

In Information Systems

1. Xiangnan He
2. Julian McAuley
3. Xing Xie
4. Steffen Rendle
5. Yongfeng Zhang
6. Hao Wang
7. Tat-seng Chua
8. Yue Shi

In Statistical and Nonlinear Physics

1. Hao Wang
2. Dit-Yan Yeung
3. Julian McAuley
4. Alex Smola
5. Hongyuan Zha
6. Hang Li
7. Wu-Jun Li
8. James She

In Representation & Self-Supervised Learning

1. Qiang Yang
2. Dit-Yan Yeung
3. Hao Wang
4. Xing Xie
5. Hongwei Wang
6. Fuzheng Zhang
7. Alex Smola
8. James She

Citations in the corpus

• Collaborative Deep Learning for Recommender Systems (2014, methodology): “Hybrid methods [1, 18, 12] seek to get the best of both worlds by combining content-based and CF-based methods.”
• DKN: Deep Knowledge-Aware Network for News Recommendation (2018, methodology): “Traditional methods [1, 43] usually represent sentences using the bag-of-words (BOW) technique, i.e., taking word counting statistics as the feature of sentences.”
• Modeling Consumer Preferences and Price Sensitivities from Large-Scale Grocery Shopping Transaction Logs (2017, methodology): “Of particular interest, feature-based matrix factorization techniques have been proposed [3,4,27,28,30] and efficient tools (e.”
• Ask the GRU: Multi-task Learning for Deep Text Recommendations (2016, methodology): “These can be used as features X j in (3) [16, 29].”
• Challenging the Long Tail Recommendation (2012, background): “Recently, various latent factor models, such as matrix factorization model [1, 2, 16] and probabilistic topic model [15, 5], have been proposed to make recommendations.”
• Collaborative Denoising Auto-Encoders for Top-N Recommender Systems (2016, background): “In some cases, y ui are numeric ratings in the range of, say, [1 , 5] or binary values { 0 , 1 } .”
• 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.”
• A Meta-Learning Perspective on Cold-Start Recommendations for Items (2017, background): “In order to address the cold-start problem, work such as [3, 14, 27, 17] has extended the MF model so that user- and item-specific terms can be included in their respective representations.”
• Adaptive bootstrapping of recommender systems using decision trees (2011, background): “Two notable works, which were published recently, are [1, 7].”
• Speedup Matrix Completion with Side Information: Application to Multi-Label Learning (2013, background): “Although several studies exploit side information for matrix recovery [1, 2, 3, 16, 29, 32, 33], most of them focus on matrix factorization techniques, which usually result in non-convex optimization problems without guarantee of perfectly recovering the target matrix.”
• General Functional Matrix Factorization Using Gradient Boosting (2013, methodology): “The use of auxiliary information in matrix factorization has been studied, various models (Agarwal & Chen, 2009; Rendle et al., 2011; Weston et al., 2012) have been proposed.”
• TFMAP: optimizing MAP for top-n context-aware recommendation (2012, unknown): “Factor models have been shown to perform well in terms of predictive accuracy and scalability [2, 18, 26].”
• Collaborative Filtering beyond the User-Item Matrix (2014, background): “In particular, one of the most influential frameworks is regression-based latent factor models [Agarwal and Chen 2009], which were proposed to integrate attributes of both users and items with U-I preference data into a generalized linear model for preference prediction.”
• User Preference Learning with Multiple Information Fusion for Restaurant Recommendation (2014, methodology): “We add the bias effect t = λf to formulate user preference as γij = λf + u > i vj where f ∈ R is a vectorized concatenation of user dependent features fi ∈ R and restaurant dependent features fj ∈ R , t is regressed using both user dependent features and restaurant dependent features with λ as coeff”
• Multiple domain user personalization (2011, methodology): “Many methods have been developed to tackle this problem typically by making use of additional information about the user (such as age, gender and occupation) [2].”
• Learning Hidden Features for Contextual Bandits (2016, methodology): “Some recent developments include sideinformation for latent factor learning [2, 11, 18] to alleviate the cold-start challenge.”
• Current challenges and visions in music recommender systems research (2017, background): “Although not designed specifically for the music domain, the authors of [4] provide an interesting liter-”
• Jointly modeling aspects, ratings and sentiments for movie recommendation (JMARS) (2014, background): “Regression based latent factor models (RLFM) [1] use attribute features to solve this problem by incorporating observable features into latent factors.”
• Sparse linear methods with side information for top-n recommendations (2012, methodology): “Such approaches include hybrid methods [5], matrix/tensor factorization [14, 8], and other regression methods [1].”
• Link Prediction via Matrix Factorization (2011, background): “Recent advances in this literature are based on inferring reasonable values of latent features by falling back to the side information as a prior [2,12].”