Regularizing Matrix Factorization with User and Item Embeddings for Recommendation.

Following recent successes in exploiting both latent factor and word embedding models in recommendation, we propose a novel Regularized Multi-Embedding (RME) based recommendation model that simultaneously ... In addition, under the cold-start scenario for users with the lowest number of interactions, against the competing models, the RME outperforms NDCG@5 by 20.2% and 29.4% in MovieLens-10M and MovieLens-20M ... [6] co-factorized the useritem interaction matrix, user-list interaction matrix, and item-list co-occurrences to recommend songs and lists of songs for users. ...

doi:10.1145/3269206.3271730 dblp:conf/cikm/TranLL018 fatcat:7xynwuipl5fa7k6tjgzmo4dtge

Multiple Versions

We propose an algorithm (SiMCa) based on matrix factorization enhanced with optimal transport steps to model user-item affinities and learn item embeddings from observed data. ... In most of these algorithms, the predictions are built upon user-item affinity scores which are obtained from high-dimensional embeddings of items and users. ... Matrix factorization characterizes every user i and item j by high-dimensional embeddings u i , v j , and predict the user-item affinity by the inner product u i , v j . ...

arXiv:2203.10107v1 fatcat:iaxj7h5o5rbzri2pbd2ygpgrku

The two parts are connected into an end-to-end network with cascading style, which guarantees that representations for item associations and sequential relationships are learned simultaneously and make ... In this paper, we propose a unified method that incorporates item association and sequential relationships for sequential recommendation. ... And Z seq ∈ R N ×d is the item embedding shared by both the sequential recommendation module and SPPMI matrix factorization module. Z con ∈ R N ×d is the item context embedding for Z seq . ...

arXiv:1910.07792v1 fatcat:anckr553fnckrenspenxquli2m

The diffusion of users' preferences is built on a layer-wise diffusion manner, with the initial user embedding as a function of the current user's features and a free base user latent vector that is not ... Furthermore, we show that our proposed model is flexible when user and item features are not available. ... To tackle these challenges, we focus on how to model user latent embedding matrix U and item latent embedding matrix V for social recommendation, where the influence propagation and associated attributes ...

arXiv:1811.02815v2 fatcat:rg7ak7rywfbjxlljcfdrdcvhsa

Multiple Versions

Matrix factorization learned by implicit alternating least squares (iALS) is a popular baseline in recommender system research publications. iALS is known to be one of the most computationally efficient ... However, recent studies suggest that its prediction quality is not competitive with the current state of the art, in particular autoencoders and other item-based collaborative filtering methods. ... Model and Loss iALS uses the matrix factorization model for scoring a user-item pair. ...

arXiv:2110.14037v1 fatcat:pvmexlekgnhcfley7zzgm2fv34

A large portion of existing social recommendation models are based on the tractable assumption that users consider the same factors to make decisions in both recommender systems and social networks. ... In this paper, we investigate how to exploit the differences between user preference in recommender systems and that in social networks, with the aim to further improve the social recommendation. ... Assume that a recommender system includes a user set P with m users and an item set Q with n items. ...

doi:10.1609/aaai.v32i1.11245 fatcat:i2cq6jaho5fitm2abhpkc54kfm

In addition, we leverage deep Autoencoders to initialize users and items latent factors, and deep embedding method gathers users' latent factors from the user trust graph. ... Recommender systems are the techniques for massively filtering information and offering the items that users find them satisfying and interesting. ... They propose an MF model to simultaneously decomposition the user-item interaction matrix and the item-to-item co-occurrence matrix with similar items factors. Zhao et al. ...

arXiv:2004.08100v8 fatcat:olpgxe5u5zg3tphqbofgdfilmu

Multiple Versions

Then, the auto-encoder is used to learn the co-occurrence embedding of each user with the correlation regularization method. ... matrix embedding part; (2) the collaborative neural recommendation part. ... We extracted the user co-occurrence matrix from the user rating matrix, with the implicit feedback matrix as input, and adopt a well-designed co-occurrence embedding regularization strategy to learn better ...

doi:10.1109/access.2021.3133628 fatcat:orzxvqybzvdennee63trnhb2ey

DOAJ

This enables recommendations for new, unseen content, and may generalize better, since the factors for all items are produced by a compactly-parametrized model. ... In a variety of application domains the content to be recommended to users is associated with text. ... Latent Factor Models Latent factor models [6] for content recommendation learn K dimensional vector embeddings of items and users: rij = bi + bj +ũ T iṽj , (1) bi, bj are user and item specific biases ...

doi:10.1145/2959100.2959180 dblp:conf/recsys/BansalBM16 fatcat:gubzk443kvfndf3nsjvhew2q64

Multiple Versions

In this survey, we review the development of recommendation frameworks with the focus on heterogeneous relational learning, which consists of different types of dependencies among users and items. ... We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information. ... The nature of graph neural networks is able to jointly maintain user-user and user-item relational structures, for generating contextualized user and item embeddings. ...

arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

Aiming to further enrich the user model with explicit feedback, this paper proposes a user embedding model for rating prediction in SVD++-based collaborative filtering, named UE-SVD++. ... In addition, the user embedding matrix is added to the existing user bias and implicit parameters in the SVD++ to increase the accuracy of the user modeling. ... The authors would like to thank the anonymous reviewers for their constructive comments that helped to improve the quality of this paper. ...

doi:10.3390/sym12010121 fatcat:bch3mhxmofbzpimrbfufisxqvm

DOAJ Szczepanski

In this paper, we present EER, a linear model for the top-N recommendation task, which takes advantage of user and item embeddings for improving novelty and diversity without harming accuracy. ... Nowadays, item recommendation is an increasing concern for many companies. Users tend to be more reactive than proactive for solving information needs. ... User and Item Embeddings Product As representations of users and items in a space with much lower dimensionality, prefs2vec embeddings can be viewed as latent vectors. ...

doi:10.1007/978-3-030-45442-5_27 fatcat:rengpdow5zfvji7gdrpd3jhswq

In this work, we present a graph neural network recommender system using item hierarchy graphs and a bespoke architecture to handle the cold start case for items. ... The experimental study on multiple datasets and millions of users and interactions indicates that our method achieves better forecasting quality than the state-of-the-art with a comparable computational ... Other sections were supported by the Mexican National Council for Science and Technology (CONACYT), 2018-000009-01EXTF-00154. ...

arXiv:2009.03455v2 fatcat:7c7yezw2dvar7kirv5cn6u5nza

Multiple Versions

Social relations provide an independent source of information about users and can be exploited for improving recommendation performance. ... Recommender systems suggest to users the items that are potentially of their interests, by mining users' feedback data on items. ... SoReg integrates social relations as regularization term in matrix factorization model with feedback-based similarities as regularization coefficients, leading to that friends share similar embeddings. ...

doi:10.1007/978-3-030-47426-3_10 fatcat:g5xojzdmibchdjvbumqxpcq74i

In modern recommender systems, matrix factorization has been widely used to decompose the user–item matrix into user and item latent factors. ... interaction matrix and the item–item cooccurrence with shared latent factors. ... Weighted regularized matrix factorization (WRMF) is an item ranking test model with positive and negative preferences [2] . ...

doi:10.3390/sym12040512 fatcat:lwpr5q4w2rcjxbp5y6h65feh7q

DOAJ Szczepanski

Regularizing Matrix Factorization with User and Item Embeddings for Recommendation

Preserved Fulltext

SiMCa: Sinkhorn Matrix Factorization with Capacity Constraints [article]

Preserved Fulltext

Cascading: Association Augmented Sequential Recommendation [article]

Preserved Fulltext

SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation [article]

Preserved Fulltext

Revisiting the Performance of iALS on Item Recommendation Benchmarks [article]

Preserved Fulltext

Social Recommendation with an Essential Preference Space

Preserved Fulltext

Recommendation system using a deep learning and graph analysis approach [article]

Preserved Fulltext

Other Versions

Neural Collaborative Autoencoder for Recommendation with Co-occurrence Embedding

Preserved Fulltext

Ask the GRU

Preserved Fulltext

Other Versions

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Preserved Fulltext

User Embedding for Rating Prediction in SVD++-Based Collaborative Filtering

Preserved Fulltext

Novel and Diverse Recommendations by Leveraging Linear Models with User and Item Embeddings [chapter]

Preserved Fulltext

Addressing Cold Start in Recommender Systems with Hierarchical Graph Neural Networks [article]

Preserved Fulltext

Modeling Users' Multifaceted Interest Correlation for Social Recommendation [chapter]

Preserved Fulltext

Metric Factorization with Item Cooccurrence for Recommendation

Preserved Fulltext