Filters








170,897 Hits in 3.8 sec

Bounded-SVD: A Matrix Factorization Method with Bound Constraints for Recommender Systems

Bang Hai Le, Kien Quang Nguyen, Ruck Thawonmas
2015 2015 International Conference on Emerging Information Technology and Engineering Solutions  
In this paper, we present a new matrix factorization method for recommender system problems, named bounded-SVD, which utilizes the constraint that all the ratings in the rating matrix are bounded within  ...  For evaluation, we compare the performance of bounded-SVD with an existing method, called Bounded Matrix Factorization (BMF), which also uses the bound constraints on the ratings.  ...  There are many matrix factorization methods for recommender systems proposed over the last decade.  ... 
doi:10.1109/eites.2015.10 fatcat:pkm7d5ribvgjhaclxu677z72sm

An Extension for Bounded-SVD — A Matrix Factorization Method with Bound Constraints for Recommender Systems

Bang Hai Le, Kazuki Mori, Ruck Thawonmas
2016 Journal of Information Processing  
In this paper, we introduce a new extension for bounded-SVD, i.e., a matrix factorization (MF) method with bound constraints for recommender system.  ...  Bounded-SVD bias takes into account the rating biases of users and items -known to reside in recommender system data.  ...  Introduction Matrix factorization (MF) [1] is one of the state-of-the-art collaborative filtering approaches to recommender systems.  ... 
doi:10.2197/ipsjjip.24.314 fatcat:zrb7gyogpjam3ksr4mw4yroxea

Bounded Matrix Low Rank Approximation [chapter]

Ramakrishnan Kannan, Mariya Ishteva, Barry Drake, Haesun Park
2015 Signals and Communication Technology  
We present substantial experimental results illustrating that the proposed method outperforms the state of the art algorithms for recommender systems such as Stochastic Gradient Descent, Alternating Least  ...  In this paper, we propose a new matrix lower rank approximation called Bounded Matrix Low Rank Approximation (BMA) which imposes a lower and an upper bound on every element of a lower rank matrix that  ...  all items i In this section, we explain the important milestones in matrix factorization for recommender systems.  ... 
doi:10.1007/978-3-662-48331-2_4 fatcat:wxtdcaqrqza6fkvut3ynmcbtu4

Bounded Matrix Low Rank Approximation

Ramakrishnan Kannan, Mariya Ishteva, Haesun Park
2012 2012 IEEE 12th International Conference on Data Mining  
We present substantial experimental results illustrating that the proposed method outperforms the state of the art algorithms for recommender systems such as Stochastic Gradient Descent, Alternating Least  ...  In this paper, we propose a new matrix lower rank approximation called Bounded Matrix Low Rank Approximation (BMA) which imposes a lower and an upper bound on every element of a lower rank matrix that  ...  all items i In this section, we explain the important milestones in matrix factorization for recommender systems.  ... 
doi:10.1109/icdm.2012.131 dblp:conf/icdm/KannanIP12 fatcat:bt2i6dfhwjcnvioc6fmgo4k4xu

Local Differentially Private Matrix Factorization with MoG for Recommendations [chapter]

Jeyamohan Neera, Xiaomin Chen, Nauman Aslam, Zhan Shu
2020 Lecture Notes in Computer Science  
To tackle privacy and utility issues with untrustworthy DA in recommendation systems, we propose a novel LDP matrix factorization (MF) with mixture of Gaussian (MoG).  ...  Unethical data aggregation practices of many recommendation systems have raised privacy concerns among users.  ...  latent factor matrix V .  ... 
doi:10.1007/978-3-030-49669-2_12 fatcat:iy65hsczvveo5crceu2vdxq5e4

Magnitude Bounded Matrix Factorisation for Recommender Systems [article]

Shuai Jiang, Kan Li, Richard Yi Da Xu
2018 arXiv   pre-print
Low rank matrix factorisation is often used in recommender systems as a way of extracting latent features.  ...  when applied on large scale recommender systems.  ...  In this paper, we propose a novel model called, Magnitude Bounded Matrix Factorisation (MBMF), which is a bounding model designed for large and sparse recommender systems.  ... 
arXiv:1807.05515v1 fatcat:htjg76kawne57e35ra5dmdgslu

Private and Utility Enhanced Recommendations with Local Differential Privacy and Gaussian Mixture Model [article]

Jeyamohan Neera, Xiaomin Chen, Nauman Aslam, Kezhi Wang, Zhan Shu
2021 arXiv   pre-print
To address this issue, we propose an LDP-based Matrix Factorization (MF) with a Gaussian Mixture Model (MoG).  ...  Our proposed LDP based recommendation system improves the recommendation accuracy without violating LDP principles.  ...  Matrix Factorization Matrix Factorization algorithm is the state-of-the-art technology used in CF-based recommendation systems.  ... 
arXiv:2102.13453v2 fatcat:2272266agjcu3iecib7rtbfjs4

Cosine Based Latent Factor Model for Precision Oriented Recommendation

Bipul Kumar, Abhishek Srivastava, Pradip Kumar
2016 International Journal of Advanced Computer Science and Applications  
The continuing research in recommender systems have primarily focused on developing algorithms for rating prediction task.  ...  Recommender systems suggest a list of interesting items to users based on their prior purchase or browsing behaviour on e-commerce platforms.  ...  Due to growing significance of RS, several techniques for developing the recommendation systems have been studied.  ... 
doi:10.14569/ijacsa.2016.070161 fatcat:yjg4tedcpnfofi6bl5spwkavma

Group-Aware Recommendation using Random Forest Classification for Sparsity Problem

D. Agalya, V. Subramaniyaswamy
2016 Indian Journal of Science and Technology  
Findings: The proposed work is based on matrix factorization to predict the missed values in the rating matrix and exclusively constructs approximation matrix to increase the prediction accuracy using  ...  the coordinate system transfer method.  ...  Authors also thank SASTRA University, Thanjavur, for providing the infrastructural facilities to carry out this research work.  ... 
doi:10.17485/ijst/2016/v9i48/107960 fatcat:mscko5jgnfe43o5higic7je26i

Recommendations as Treatments: Debiasing Learning and Evaluation [article]

Tobias Schnabel, Adith Swaminathan, Ashudeep Singh, Navin Chandak and Thorsten Joachims
2016 arXiv   pre-print
Most data for evaluating and training recommender systems is subject to selection biases, either through self-selection by the users or through the actions of the recommendation system itself.  ...  The approach leads to unbiased performance estimators despite biased data, and to a matrix factorization method that provides substantially improved prediction performance on real-world data.  ...  For the task of learning recommender systems, we show that our new matrix factorization method substantially outperforms methods that ignore selection bias, as well as existing state-of-the-art methods  ... 
arXiv:1602.05352v2 fatcat:lgz2h3fp7jgwtkzlpm2dpaw73m

Probabilistic Matrix Factorization with Personalized Differential Privacy [article]

Shun Zhang, Laixiang Liu, Zhili Chen, Hong Zhong
2018 arXiv   pre-print
Probabilistic matrix factorization (PMF) plays a crucial role in recommendation systems.  ...  We then develop a modified sampling mechanism (with bounded differential privacy) for achieving PDP.  ...  For building recommendation systems, probabilistic matrix factorization (PMF) is a prevailing method [23] that performs well on large and sparse datasets.  ... 
arXiv:1810.08509v1 fatcat:s3wrde57jrfe3m7wqnxh5w6c4e

Sequential Matrix Completion [article]

Annie Marsden, Sergio Bacallado
2017 arXiv   pre-print
We propose a novel algorithm for sequential matrix completion in a recommender system setting, where the (i,j)th entry of the matrix corresponds to a user i's rating of product j.  ...  The objective of the algorithm is to provide a sequential policy for user-product pair recommendation which will yield the highest possible ratings after a finite time horizon.  ...  Much research on recommender systems has focused on the matrix completion problem.  ... 
arXiv:1710.08045v1 fatcat:rvq46bb2wfh5nj4nftytfrewsm

Active Learning in Recommendation Systems with Multi-level User Preferences [article]

Yuheng Bu, Kevin Small
2018 arXiv   pre-print
algorithm for practical recommendations.  ...  In this work, we study the active learning problem with multi-level user preferences within the collective matrix factorization (CMF) framework.  ...  Collective Factorization Model The collective matrix factorization model (Singh and Gordon 2008; Gupta and Singh 2015) extends the commonly used matrix factorization model to multiple matrices by assigning  ... 
arXiv:1811.12591v1 fatcat:czcqgie2onfn7blkf5fm4wa45y

Differentially private recommender systems

Frank McSherry, Ilya Mironov
2009 Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09  
We consider the problem of producing recommendations from collective user behavior while simultaneously providing guarantees of privacy for these users.  ...  To adapt these algorithms, we explicitly factor them into two parts, an aggregation/learning phase that can be performed with differential privacy guarantees, and an individual recommendation phase that  ...  The goals of improving accuracy of recommender systems and providing privacy for their users are nicely aligned.  ... 
doi:10.1145/1557019.1557090 dblp:conf/kdd/McSherryM09 fatcat:kmaoctvqvbcitoy5qju5m3xls4

A quantum-inspired classical algorithm for recommendation systems [article]

Ewin Tang
2019 arXiv   pre-print
We give a classical analogue to Kerenidis and Prakash's quantum recommendation system, previously believed to be one of the strongest candidates for provably exponential speedups in quantum machine learning  ...  Further, under strong input assumptions, the classical recommendation system resulting from our algorithm produces recommendations exponentially faster than previous classical systems, which run in time  ...  The guarantee on our output matrix D is (♦), but for our recommendation system, we want that D is close to some A σ,η .  ... 
arXiv:1807.04271v2 fatcat:qjxdqtl6dnhtvkbycjwlvfecoq
« Previous Showing results 1 — 15 out of 170,897 results