Enriching Non-negative Matrix Factorization with Contextual Embeddings for Recommender Systems

Khan, Zafran; Iltaf, Naima; Afzal, Hammad; Abbas, Haider

doi:10.1016/j.neucom.2019.09.080

Cited by 33 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Matrix factorization (MF) is a well-known mathematical scheme that has recently been applied to a range of complex problems in the numerical linear algebra, machine learning and computational biology. Some notable examples include Eigendecomposition of a matrix [36], Data Compression [37], Recommender Systems [38], Spectral Clustering [24], and gene expression analysis [39]. Some of the MF-based techniques that have been used widely are Singular Value Decomposition (SVD) [40], Principle Component Analysis (PCA) [41], and Probabilistic Matrix Factorization (PMF) [42].…”

Section: Matrix Factorizationmentioning

confidence: 99%

See 1 more Smart Citation

Decoding Clinical Biomarker Space of COVID-19: Exploring Matrix Factorization-based Feature Selection Methods

Saberi-Movahed

Mohammadifard

Mehrpooya

et al. 2021

Preprint

View full text Add to dashboard Cite

One of the most critical challenges in managing complex diseases like COVID-19 is to establish an intelligent triage system that can optimize the clinical decision-making at the time of a global pandemic. The clinical presentation and patients’ characteristics are usually utilized to identify those patients who need more critical care. However, the clinical evidence shows an unmet need to determine more accurate and optimal clinical biomarkers to triage patients under a condition like the COVID-19 crisis. Here we have presented a machine learning approach to find a group of clinical indicators from the blood tests of a set of COVID-19 patients that are predictive of poor prognosis and morbidity. Our approach consists of two interconnected schemes: Feature Selection and Prognosis Classification. The former is based on different Matrix Factorization (MF)-based methods, and the latter is performed using Random Forest algorithm. Our model reveals that Arterial Blood Gas (ABG) O2 Saturation and C-Reactive Protein (CRP) are the most important clinical biomarkers determining the poor prognosis in these patients. Our approach paves the path of building quantitative and optimized clinical management systems for COVID-19 and similar diseases.

show abstract

Section: Matrix Factorizationmentioning

confidence: 99%

“…in which n and d denote the number of samples and that of features, respectively. The To decompose a given (non-negative) matrix into the product of two low-rank (non-negative) matrices [24,27,36,37,38,39,40,41,42,43,44,45,46,47,48] Subspace Learning…”

Section: Notationsmentioning

confidence: 99%

Decoding Clinical Biomarker Space of COVID-19: Exploring Matrix Factorization-based Feature Selection Methods

Saberi-Movahed

Mohammadifard

Mehrpooya

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Social relationship and reviews information are used as auxiliary information to improve recommendation performance. Zafran Khan et al [25] propose a context-based recommendation model to improve item feature extraction, which extracts context features through convolutional neural network (CNN), it not only resolve the sparsity problem, but also addresses the information loss due to the negative values in latent factors. Although both of them introduce auxiliary information to improve recommendation performance, they ignore the interaction between different features.…”

Section: Related Workmentioning

confidence: 99%

Information Fusion-Based Deep Neural Attentive Matrix Factorization Recommendation

et al. 2021

View full text Add to dashboard Cite

The emergence of the recommendation system has effectively alleviated the information overload problem. However, traditional recommendation systems either ignore the rich attribute information of users and items, such as the user’s social-demographic features, the item’s content features, etc., facing the sparsity problem, or adopt the fully connected network to concatenate the attribute information, ignoring the interaction between the attribute information. In this paper, we propose the information fusion-based deep neural attentive matrix factorization (IFDNAMF) recommendation model, which introduces the attribute information and adopts the element-wise product between the different information domains to learn the cross-features when conducting information fusion. In addition, the attention mechanism is utilized to distinguish the importance of different cross-features on prediction results. In addition, the IFDNAMF adopts the deep neural network to learn the high-order interaction between users and items. Meanwhile, we conduct extensive experiments on two datasets: MovieLens and Book-crossing, and demonstrate the feasibility and effectiveness of the model.

show abstract

“…, ). By combining the objective function of three models (5), (13) and (15), the final model of the MCoC-based collaborative recommendation system is obtained which is as follows:…”

Section: Grouping Two Items Togethermentioning

confidence: 99%

“…Multi-class Co-Clustering (MCoC) is a co-clustering method which allows each user or item becomes the members of several groups [14]. To estimate unrated items of each group in MCoC, for each group, an independent collaborative filtering approach such as slope-one approach or matrix factorization approach [15] is implemented [16]. Coclustering can also alleviate cold start problem of recommendation systems [13].…”

Section: Introductionmentioning

confidence: 99%

Improving Multi-class Co-Clustering-Based Collaborative Recommendation Using Item Tags

Gholami¹,

Forghani²

2020

RIA

View full text Add to dashboard Cite

Multi-class Co-Clustering (MCoC)-based recommendation system is a method for recommending favorite items to users. It, firstly, groups items and users in a way that users have common interests and their favored items are put in the same group. Then, to estimate unrated items of each group, for each group, an independent collaborative filtering approach is implemented. MCoC-based recommendation system uses rating vectors to determine similar items and to group them together. We expect that the ratings of two items with the same tag be closer than two items with different tags. Therefore, tags can also be used to determine similar items for co-clustering. The purpose of this study is to enhance the performance of co-clustering to increase the accuracy of MCoC-based recommendation system by using item tags in addition to item rating vectors. Our experiments show that mean absolute error of our proposed method is much less than that of MCoC-based recommendation system.

show abstract

Enriching Non-negative Matrix Factorization with Contextual Embeddings for Recommender Systems

Cited by 33 publications

References 16 publications

Decoding Clinical Biomarker Space of COVID-19: Exploring Matrix Factorization-based Feature Selection Methods

Decoding Clinical Biomarker Space of COVID-19: Exploring Matrix Factorization-based Feature Selection Methods

Information Fusion-Based Deep Neural Attentive Matrix Factorization Recommendation

Improving Multi-class Co-Clustering-Based Collaborative Recommendation Using Item Tags

Contact Info

Product

Resources

About