scholarly journals Multi-Feature Discrete Collaborative Filtering for Fast Cold-Start Recommendation

2020 ◽  
Vol 34 (01) ◽  
pp. 270-278
Author(s):  
Yang Xu ◽  
Lei Zhu ◽  
Zhiyong Cheng ◽  
Jingjing Li ◽  
Jiande Sun
Keyword(s):  
Collaborative Filtering ◽  
Large Scale ◽  
Feature Fusion ◽  
Computation Time ◽  
Cold Start ◽  
User Preferences ◽  
Low Rank ◽  
Specific Content ◽  
Hash Codes ◽  
Content Feature

Hashing is an effective technique to address the large-scale recommendation problem, due to its high computation and storage efficiency on calculating the user preferences on items. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Their recommendation process mainly relies on the user-item interactions and single specific content feature. When the interaction history or the content feature is unavailable (the cold-start problem), their performance will be seriously deteriorated. 2) Existing methods learn the hash codes with relaxed optimization or adopt discrete coordinate descent to directly solve binary hash codes, which results in significant quantization loss or consumes considerable computation time. In this paper, we propose a fast cold-start recommendation method, called Multi-Feature Discrete Collaborative Filtering (MFDCF), to solve these problems. Specifically, a low-rank self-weighted multi-feature fusion module is designed to adaptively project the multiple content features into binary yet informative hash codes by fully exploiting their complementarity. Additionally, we develop a fast discrete optimization algorithm to directly compute the binary hash codes with simple operations. Experiments on two public recommendation datasets demonstrate that MFDCF outperforms the state-of-the-arts on various aspects.

Modelling trust networks using resistive circuits for trust-aware recommender systems

2016 ◽  
Vol 43 (1) ◽  
pp. 135-144 ◽  
Author(s):  
Mehdi Hosseinzadeh Aghdam ◽  
Morteza Analoui ◽  
Peyman Kabiri
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Cold Start ◽  
User Preferences ◽  
Item Selection ◽  
Trust Networks ◽  
Trust Inference ◽  
Trust Information

Recommender systems have been widely used for predicting unknown ratings. Collaborative filtering as a recommendation technique uses known ratings for predicting user preferences in the item selection. However, current collaborative filtering methods cannot distinguish malicious users from unknown users. Also, they have serious drawbacks in generating ratings for cold-start users. Trust networks among recommender systems have been proved beneficial to improve the quality and number of predictions. This paper proposes an improved trust-aware recommender system that uses resistive circuits for trust inference. This method uses trust information to produce personalized recommendations. The result of evaluating the proposed method on Epinions dataset shows that this method can significantly improve the accuracy of recommender systems while not reducing the coverage of recommender systems.

scholarly journals A Hybrid Deep Collaborative Filtering Approach for Recommender Systems

2021 ◽  
Author(s):  
Kirubahari R ◽  
Miruna Joe Amali S
Keyword(s):  
Singular Value Decomposition ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Cold Start ◽  
Singular Value ◽  
User Preferences ◽  
Boltzmann Machine ◽  
Latent Features ◽  
Value Decomposition ◽  
Cold Start Problem

Abstract Recommender Systems (RS) help the users by showing better products and relevant items efficiently based on their likings and historical interactions with other users and items. Collaborative filtering is one of the most powerful technique of recommender system and provides personalized recommendation for users by prediction rating approach. Many Recommender Systems generally model only based on user implicit feedback, though it is too challenging to build RS. Conventional Collaborative Filtering (CF) techniques such as matrix decomposition, which is a linear combination of user rating for an item with latent features of user preferences, but have limited learning capacity. Additionally, it has been suffering from data sparsity and cold start problem due to insufficient data. In order to overcome these problems, an integration of conventional collaborative filtering with deep neural networks is proposed. A Weighted Parallel Deep Hybrid Collaborative Filtering based on Singular Value Decomposition (SVD) and Restricted Boltzmann Machine (RBM) is proposed for significant improvement. In this approach a user-item relationship matrix with explicit ratings is constructed. The user - item matrix is integrated to Singular Value Decomposition (SVD) that decomposes the matrix into the best lower rank approximation of the original matrix. Secondly the user-item matrix is embedded into deep neural network model called Restricted Boltzmann Machine (RBM) for learning latent features of user- item matrix to predict user preferences. Thus, the Weighted Parallel Deep Hybrid RS uses additional attributes of user - item matrix to alleviate the cold start problem. The proposed method is verified using two different movie lens datasets namely, MovieLens 100K and MovieLens of 1M and evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The results indicate better prediction compared to other techniques in terms of accuracy.

scholarly journals Ensemble Based Hybrid Recommender Systems

2020 ◽  
Vol 9 (3) ◽  
pp. 826-833
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Nearest Neighbor ◽  
Demographic Data ◽  
Weighted Average ◽  
Cold Start ◽  
User Preferences ◽  
Vector Method ◽  
Hybrid Recommender Systems ◽  
Hybrid Recommender

In the past few years, the advent of computational and prediction technologies has spurred a lot of interest in recommendation research. Content-based recommendation and collaborative filtering are two elementary ways to build recommendation systems. In a content based recommender system, products are described using keywords and a user profile is developed to enlist the type of products the user may like. Widely used Collaborative filtering recommender systems provide recommendations based on similar user preferences. Hybrid recommender systems are a blend of content-based and collaborative techniques to harness their advantages to maximum. Although both these methods have their own advantages, they fail in ‘cold start’ situations where new users or products are introduced to the system, and the system fails to recommend new products as there is no usage history available for these products. In this work we work on MovieLens 100k dataset to recommend movies based on the user preferences. This paper proposes a weighted average method for combining predictions to improve the accuracy of hybrid models. We used standard error as a measure to assign the weights to the classifiers to approximate their participation in predicting the recommendations. The cold start problem is addressed by including demographic data of the user by using three approaches namely Latent Vector Method, Bayesian Weighted Average, and Nearest Neighbor Algorithm.

scholarly journals Matrix Factorization Techniques for Context-Aware Collaborative Filtering Recommender Systems: A Survey

2018 ◽  
Vol 11 (2) ◽  
pp. 1 ◽  
Author(s):  
Mohamed Hussein Abdi ◽  
George Onyango Okeyo ◽  
Ronald Waweru Mwangi
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Matrix Factorization ◽  
Large Scale ◽  
User Preferences ◽  
Online Information ◽  
Context Aware ◽  
Preference Rating ◽  
Accessible Information ◽  
The Impact

Collaborative Filtering Recommender Systems predict user preferences for online information, products or services by learning from past user-item relationships. A predominant approach to Collaborative Filtering is Neighborhood-based, where a user-item preference rating is computed from ratings of similar items and/or users. This approach encounters data sparsity and scalability limitations as the volume of accessible information and the active users continue to grow leading to performance degradation, poor quality recommendations and inaccurate predictions. Despite these drawbacks, the problem of information overload has led to great interests in personalization techniques. The incorporation of context information and Matrix and Tensor Factorization techniques have proved to be a promising solution to some of these challenges. We conducted a focused review of literature in the areas of Context-aware Recommender Systems utilizing Matrix Factorization approaches. This survey paper presents a detailed literature review of Context-aware Recommender Systems and approaches to improving performance for large scale datasets and the impact of incorporating contextual information on the quality and accuracy of the recommendation. The results of this survey can be used as a basic reference for improving and optimizing existing Context-aware Collaborative Filtering based Recommender Systems. The main contribution of this paper is a survey of Matrix Factorization techniques for Context-aware Collaborative Filtering Recommender Systems. 

Utilizing Association Rules for Improving the Performance of Collaborative Filtering

2012 ◽  
Vol 3 (2) ◽  
pp. 14-28 ◽  
Author(s):  
Zainab Khanzadeh ◽  
Mehregan Mahdavi
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Association Rules ◽  
Cold Start ◽  
User Preferences ◽  
Experimental Results ◽  
Internet Technology ◽  
Promising Technique ◽  
Novel Approach ◽  
Better Than

Internet technology has rapidly grown during the last decades. Presently, users are faced with a great amount of information and they need help to find appropriate items in the shortest possible time. Recommender systems were introduced to overcome this problem of overloaded information. They recommend items of interest to users based on their expressed preferences. Major e-commerce companies try to use this technology to increase their sales. Collaborative Filtering is the most promising technique in recommender systems. It provides personalized recommendations according to user preferences. But one of the problems of Collaborative Filtering is cold-start. The authors provide a novel approach for solving this problem through using the attributes of items in order to recommend items to more people for improving e-business activities. The experimental results show that the proposed method performs better than existing methods in terms of the number of generated recommendations and their quality.

scholarly journals A Multi-Modality Deep Network for Cold-Start Recommendation

2018 ◽  
Vol 2 (1) ◽  
pp. 7 ◽  
Author(s):  
◽  
◽  
Keyword(s):  
Feature Extraction ◽  
Collaborative Filtering ◽  
Large Scale ◽  
Dimensional Space ◽  
Feature Space ◽  
Cold Start ◽  
Heterogeneous Data ◽  
Deep Network ◽  
Tightly Coupled ◽  
Hybrid Recommender

Collaborative filtering (CF) approaches, which provide recommendations based on ratings or purchase history, perform well for users and items with sufficient interactions. However, CF approaches suffer from the cold-start problem for users and items with few ratings. Hybrid recommender systems that combine collaborative filtering and content-based approaches have been proved as an effective way to alleviate the cold-start issue. Integrating contents from multiple heterogeneous data sources such as reviews and product images is challenging for two reasons. Firstly, mapping contents in different modalities from the original feature space to a joint lower-dimensional space is difficult since they have intrinsically different characteristics and statistical properties, such as sparse texts and dense images. Secondly, most algorithms only use content features as the prior knowledge to improve the estimation of user and item profiles but the ratings do not directly provide feedback to guide feature extraction. To tackle these challenges, we propose a tightly-coupled deep network model for fusing heterogeneous modalities, to avoid tedious feature extraction in specific domains, and to enable two-way information propagation from both content and rating information. Experiments on large-scale Amazon product data in book and movie domains demonstrate the effectiveness of the proposed model for cold-start recommendation.

Double Precision Is Not Needed for Many-Body Calculations: New Conventional Wisdom

2018 ◽  
Author(s):  
Pavel Pokhilko ◽  
Evgeny Epifanovsky ◽  
Anna I. Krylov
Keyword(s):  
Large Scale ◽  
Computation Time ◽  
Coupled Cluster ◽  
Double Precision ◽  
Many Body ◽  
Single Precision ◽  
Parallel Performance ◽  
Point Representation ◽  
Electron Repulsion Integrals ◽  
Cluster Methods

Using single precision floating point representation reduces the size of data and computation time by a factor of two relative to double precision conventionally used in electronic structure programs. For large-scale calculations, such as those encountered in many-body theories, reduced memory footprint alleviates memory and input/output bottlenecks. Reduced size of data can lead to additional gains due to improved parallel performance on CPUs and various accelerators. However, using single precision can potentially reduce the accuracy of computed observables. Here we report an implementation of coupled-cluster and equation-of-motion coupled-cluster methods with single and double excitations in single precision. We consider both standard implementation and one using Cholesky decomposition or resolution-of-the-identity of electron-repulsion integrals. Numerical tests illustrate that when single precision is used in correlated calculations, the loss of accuracy is insignificant and pure single-precision implementation can be used for computing energies, analytic gradients, excited states, and molecular properties. In addition to pure single-precision calculations, our implementation allows one to follow a single-precision calculation by clean-up iterations, fully recovering double-precision results while retaining significant savings.

Knowledge Transfer with Weighted Adversarial Network for Cold-Start Store Site Recommendation

2021 ◽  
Vol 15 (3) ◽  
pp. 1-27
Author(s):  
Yan Liu ◽  
Bin Guo ◽  
Daqing Zhang ◽  
Djamal Zeghlache ◽  
Jingmin Chen ◽  
...  
Keyword(s):  
Large Scale ◽  
Cold Start ◽  
Weighting Scheme ◽  
Training Data ◽  
Chain Store ◽  
Useful Knowledge ◽  
Adversarial Network ◽  
Brick And Mortar ◽  
New City ◽  
Learning Machine

Store site recommendation aims to predict the value of the store at candidate locations and then recommend the optimal location to the company for placing a new brick-and-mortar store. Most existing studies focus on learning machine learning or deep learning models based on large-scale training data of existing chain stores in the same city. However, the expansion of chain enterprises in new cities suffers from data scarcity issues, and these models do not work in the new city where no chain store has been placed (i.e., cold-start problem). In this article, we propose a unified approach for cold-start store site recommendation, Weighted Adversarial Network with Transferability weighting scheme (WANT), to transfer knowledge learned from a data-rich source city to a target city with no labeled data. In particular, to promote positive transfer, we develop a discriminator to diminish distribution discrepancy between source city and target city with different data distributions, which plays the minimax game with the feature extractor to learn transferable representations across cities by adversarial learning. In addition, to further reduce the risk of negative transfer, we design a transferability weighting scheme to quantify the transferability of examples in source city and reweight the contribution of relevant source examples to transfer useful knowledge. We validate WANT using a real-world dataset, and experimental results demonstrate the effectiveness of our proposed model over several state-of-the-art baseline models.

Sign in / Sign up

Export Citation Format

Share Document