Combining Matrix Factorization Research Articles

Recommender system based on collaborative filtering

Collaborative filtering is a popular technique for providing personalized recommendations in recommender systems. However, the sparsity problem and the accuracy-diversity tradeoff are major challenges that limit its performance. In this article, we propose a novel approach that combines matrix factorization with novelty metrics to improve the accuracy and diversity of recommendations. We evaluate our approach on the MovieLens dataset and compare it with several state-of-the-art techniques, including neighborhood-based methods, probabilistic models, and hybrid approaches. Our experimental results show that our method is better than other techniques in terms of both accuracy and diversity, as measured by precision, recall, and novelty metrics.

CMF-SMR: Convolutional matrix factorization for sequential movie recommendations

Recommender system (RS) has become an essential component of e-commerce, social media, and other online platforms. Collaborative filtering (CF) is one of the most commonly used techniques in RS that relies on user-item interactions to generate recommendations. However, CF suffers from the cold-start problem, sparsity, and scalability issues. To address these challenges, this work propose a hybrid system called Convolutional Matrix Factorization for Sequential Movie Recommendations (CMF-SMR), which combines matrix factorization (MF) with convolutional neural networks (CNNs). CMF-SMR leverages the non-linear feature extraction capabilities of CNNs and the representation learning abilities of deep learning to enhance the accuracy and robustness of traditional MF-based RS. Specifically, CNNs and MF were used to respectively extract features from user-item interaction data and use them as input for learning user and item representations. The learned representations are then used to predict user-item ratings. This work evaluates the performance of our proposed method on two publicly available datasets, and the experimental results demonstrate that our method outperforms several state-of-the-art techniques in terms of accuracy, scalability, and robustness. Moreover, this work conduct evaluation metrics to demonstrate the accuracy of our proposed method. Overall, our proposed CMF-SMR provides a promising solution for addressing the limitations of traditional CF-based RS and can be applied in various domains, including e-commerce, social media, and personalized content recommendation systems.

Multiview Clustering with Self Representation and Structural Constraints

Multi-view clustering, which divides objects into multiple clusters with high intra-cluster and low inter- cluster similarity for all perspectives, is of enormous significance for uncovering the mechanisms of systems. Multi-view data effectively model and characterise the underlying complex systems. Because they only consider the shared characteristics of objects or their correlation, current algorithms are criticised for their subpar performance because they ignore the heterogeneity and structural constraints of different views. A brand-new network-based method called Multi-view Clustering with Self-representation and Structural Constraints (MCSSC), which combines matrix factorization with low-rank representation of various perspectives, is presented to address these issues. In particular, a network is built for each view to reduce heterogeneity from multi-view data, converting the multi-view clustering problem into the multi-layer networks clustering problem. The MCSSC factorises network-related matrices by projecting them into a shared space and simultaneously trains an affinity graph for objects in multiple views with self-representation in order to extract the shared properties of multiple views. The structural constraint is applied to the affinity graph, where the clusters are identified, to aid with clustering. Numerous tests show that MCSSC performs noticeably better than the state-of-the-art in terms of accuracy, indicating the superiority of the suggested method

News recommendations based on collaborative topic modeling and collaborative filtering with generative adversarial networks

PurposeOnline news websites provide huge amounts of timely news, bringing the challenge of recommending personalized news articles. Generative adversarial networks (GAN) based on collaborative filtering (CFGAN) can achieve effective recommendation quality. However, CFGAN ignores item contents, which contain more latent preference features than just user ratings. It is important to consider both ratings and item contents in making preference predictions. This study aims to improve news recommendation by proposing a GAN-based news recommendation model considering both ratings (implicit feedback) and the latent features of news content.Design/methodology/approachThe collaborative topic modeling (CTM) can improve user preference prediction by combining matrix factorization (MF) with latent topics of item content derived from latent topic modeling. This study proposes a novel hybrid news recommendation model, Hybrid-CFGAN, which modifies the architecture of the CFGAN model with enhanced preference learning from the CTM. The proposed Hybrid-CFGAN model contains parallel neural networks – original rating-based preference learning and CTM-based preference learning, which consider both ratings and news content with user preferences derived from the CTM model. A tunable parameter is used to adjust the weights of the two preference learnings, while concatenating the preference outputs of the two parallel neural networks.FindingsThis study uses the dataset collected from an online news website, NiusNews, to conduct an experimental evaluation. The results show that the proposed Hybrid-CFGAN model can achieve better performance than the state-of-the-art GAN-based recommendation methods. The proposed novel Hybrid-CFGAN model can enhance existing GAN-based recommendation and increase the performance of preference predictions on textual content such as news articles.Originality/valueAs the existing CFGAN model does not consider content information and solely relies on history logs, it may not be effective in recommending news articles. Our proposed Hybrid-CFGAN model modified the architecture of the CFGAN generator by adding a parallel neural network to gain the relevant information from news content and user preferences derived from the CTM model. The novel idea of adjusting the preference learning from two parallel neural networks – original rating-based preference learning and CTM-based preference learning – contributes to improve the recommendation quality of the proposed model by considering both ratings and latent preferences derived from item contents. The proposed novel recommendation model can improve news recommendation, thereby increasing the commercial value of news media platforms.

Matrix factorization with denoising autoencoders for prediction of drug-target interactions.

Drug-target interaction is crucial in the discovery of new drugs. Computational methods can be used to identify new drug-target interactions at low costs and with reasonable accuracy. Recent studies pay more attention to machine-learning methods, ranging from matrix factorization to deep learning, in the DTI prediction. Since the interaction matrix is often extremely sparse, DTI prediction performance is significantly decreased with matrix factorization-based methods. Therefore, some matrix factorization methods utilize side information to address both the sparsity issue of the interaction matrix and the cold-start issue. By combining matrix factorization and autoencoders, we propose a hybrid DTI prediction model that simultaneously learn the hidden factors of drugs and targets from their side information and interaction matrix. The proposed method is composed of two steps: the pre-processing of the interaction matrix, and the hybrid model. We leverage the similarity matrices of both drugs and targets to address the sparsity problem of the interaction matrix. The comparison of our approach against other algorithms on the same reference datasets has shown good results regarding area under receiver operating characteristic curve and the area under precision-recall curve. More specifically, experimental results achieve high accuracy on golden standard datasets (e.g., Nuclear Receptors, GPCRs, Ion Channels, and Enzymes) when performed with five repetitions of tenfold cross-validation. Display graphical of the hybrid model of Matrix Factorization with Denoising Autoencoders with the help side information of drugs and targets for Prediction of Drug-Target Interactions.

Semi-Discrete Social Recommendation (Student Abstract)

Combining matrix factorization (MF) with network embedding (NE) has been a promising solution to social recommender systems. However, such a scheme suffers from the online predictive efficiency issue due to the ever-growing users and items. In this paper, we propose a novel hashing-based social recommendation model, called semi-discrete socially embedded matrix factorization (S2MF), which leverages the dual advantages of social information for recommendation effectiveness and hashing trick for online predictive efficiency. Experimental results demonstrate the advantages of S2MF over state-of-the-art discrete recommendation models and its real-valued competitors.

Matrix factorization with dual-network collaborative embedding for social recommendation

Combining Matrix Factorization (MF) with Network Embedding (NE) has been a promising solution to social recommender systems. However, in most of the current combined schemes, the user-specific linking proportions learned by NE are fed to the downstream MF, but not reverse, which is sub-optimal as the rating information is not utilized to discover the linking features for users. Furthermore, the existing combined models mainly focus on enhancing the representation learning for users by exploiting user–user network, yet ignore the representation improvement for items. In this paper, we propose a novel social recommendation scheme, called MF with dual-network collaborative embedding (MF-decoding), which jointly optimizes an integrated objective function of MF and NE, in which both MF and NE tasks can be mutually reinforced in a unified learning process. In particular, the explicit user–user network and the implicit item–item network are collaboratively used by MF-decoding to enhance the representation learning for users and items simultaneously. Our encouraging experimental results on three benchmarks validate the superiority of the proposed MF-decoding model over state-of-the-art social recommendation methods.

Spatial Segmentation of Mass Spectrometry Imaging Data by Combining Multivariate Clustering and Univariate Thresholding.

Spatial segmentation partitions mass spectrometry imaging (MSI) data into distinct regions, providing a concise visualization of the vast amount of data and identifying regions of interest (ROIs) for downstream statistical analysis. Unsupervised approaches are particularly attractive, as they may be used to discover the underlying subpopulations present in the high-dimensional MSI data without prior knowledge of the properties of the sample. Herein, we introduce an unsupervised spatial segmentation approach, which combines multivariate clustering and univariate thresholding to generate comprehensive spatial segmentation maps of the MSI data. This approach combines matrix factorization and manifold learning to enable high-quality image segmentation without an extensive hyperparameter search. In parallel, some ion images inadequately represented in the multivariate analysis were treated using univariate thresholding to generate complementary spatial segments. The final spatial segmentation map was assembled from segment candidates that were generated using both techniques. We demonstrate the performance and robustness of this approach for two MSI data sets of mouse uterine and kidney tissue sections that were acquired with different spatial resolutions. The resulting segmentation maps are easy to interpret and project onto the known anatomical regions of the tissue.

Discrete Two-Step Cross-Modal Hashing through the Exploitation of Pairwise Relations.

The cross-modal hashing method can map heterogeneous multimodal data into a compact binary code that preserves semantic similarity, which can significantly enhance the convenience of cross-modal retrieval. However, the currently available supervised cross-modal hashing methods generally only factorize the label matrix and do not fully exploit the supervised information. Furthermore, these methods often only use one-directional mapping, which results in an unstable hash learning process. To address these problems, we propose a new supervised cross-modal hash learning method called Discrete Two-step Cross-modal Hashing (DTCH) through the exploitation of pairwise relations. Specifically, this method fully exploits the pairwise similarity relations contained in the supervision information: for the label matrix, the hash learning process is stabilized by combining matrix factorization and label regression; for the pairwise similarity matrix, a semirelaxed and semidiscrete strategy is adopted to potentially reduce the cumulative quantization errors while improving the retrieval efficiency and accuracy. The approach further combines an exploration of fine-grained features in the objective function with a novel out-of-sample extension strategy to enable the implicit preservation of consistency between the different modal distributions of samples and the pairwise similarity relations. The superiority of our method was verified through extensive experiments using two widely used datasets.

Gene set inference from single-cell sequencing data using a hybrid of matrix factorization and variational autoencoders

Recent advances in single-cell RNA sequencing have driven the simultaneous measurement of the expression of thousands of genes in thousands of single cells. These growing datasets allow us to model gene sets in biological networks at an unprecedented level of detail, in spite of heterogeneous cell populations. Here, we propose a deep neural network model that is a hybrid of matrix factorization and variational autoencoders, which we call restricted latent variational autoencoder (resVAE). The model uses weights as factorized matrices to obtain gene sets, while class-specific inputs to the latent variable space facilitate a plausible identification of cell types. This artificial neural network model seamlessly integrates functional gene set inference, experimental covariate effect isolation, and static gene identification, which we conceptually demonstrate here for four single-cell RNA sequencing datasets. The wealth of data generated by single-cell RNA sequencing can be used to identify gene sets across cells, as well as to identify specific cells. Lukassen and colleagues propose a method combining matrix factorization and variational auto encoders that can capture both cross-cell and cell-specific information.

Sparse Data Recommendation by Fusing Continuous Imputation Denoising Autoencoder and Neural Matrix Factorization

In recent years, although deep neural networks have yielded immense success in solving various recognition and classification problems, the exploration of deep neural networks in recommender systems has received relatively less attention. Meanwhile, the inherent sparsity of data is still a challenging problem for deep neural networks. In this paper, firstly, we propose a new CIDAE (Continuous Imputation Denoising Autoencoder) model based on the Denoising Autoencoder to alleviate the problem of data sparsity. CIDAE performs regular continuous imputation on the missing parts of the original data and trains the imputed data as the desired output. Then, we optimize the existing advanced NeuMF (Neural Matrix Factorization) model, which combines matrix factorization and a multi-layer perceptron. By optimizing the training process of NeuMF, we improve the accuracy and robustness of NeuMF. Finally, this paper fuses CIDAE and optimized NeuMF with reference to the idea of ensemble learning. We name the fused model the I-NMF (Imputation-Neural Matrix Factorization) model. I-NMF can not only alleviate the problem of data sparsity, but also fully exploit the ability of deep neural networks to learn potential features. Our experimental results prove that I-NMF performs better than the state-of-the-art methods for the public MovieLens datasets.

Considering Real-Time User Participation for Anchor Recommendation on Live Streaming Platforms

In recent years, live streaming has experienced rapid growth and become a new social media with wide influence, ranking top in attracting internet traffic. On live streaming platforms, plenty of anchors simultaneously broadcast live streams on different topics. How to recommend appropriate anchors to viewers and make them stay are very important for the platforms. Different from video-sharing platforms such as YouTube, one of the major characteristics of live streaming is real-time user participation, which plays an important role in analyzing viewer's watching preferences and has not been well studied in existing research on recommendation systems. Therefore, in this paper, we study how to take real-time interactions between viewers and anchors into consideration to make a better live stream recommendation. To this end, we develop an interaction-aware recommendation framework, combining matrix factorization and deep learning models to infer viewer preferences. The matrix factorization component can effectively learn viewer preferences at the anchor level, and the deep learning component is innovatively introduced to learn viewer preferences for real-time interactive behaviors at the live stream level. This interaction-aware recommendation framework captures comprehensive relationships between real-time user participation and viewer's watching duration, which helps enhance real-time anchor recommendation performances. Comprehensive experiments conducted on a real-world dataset demonstrate that our new model significantly outperforms baselines. Interpretable viewer preferences for real-time interactive behaviors are helpful for a more profound understanding of viewer's behaviors.

Predicting process behavior meets factorization machines

Predictive business process monitoring methods use datasets of completed cases related to a process to predict the behaviour of running cases. To handle the large amounts of available event data, recent works have turned to deep learning techniques and have achieved fairly accurate results. However, results from these techniques are often difficult to interpret and explain. In the area of Recommender systems, factorization models have been an important class of predictive techniques due to its scalability and ability to infer latent features. Motivated by research in Recommender systems, this paper presents a predictive model that combines matrix factorization techniques from Recommender systems and knowledge from Business Process Management to learn interactions between latent features that can be used to predict the next event of an ongoing case. Evaluation on two real-life datasets from a Dutch Financial Institute and Volvo IT Belgium shows that the approach yields results that are comparable and at times superior to state-of-the-art techniques such as neural networks, yielding at most a precision of 0.87 for next event predictions.

TESS3: fast inference of spatial population structure and genome scans for selection.

Geography and landscape are important determinants of genetic variation in natural populations, and several ancestry estimation methods have been proposed to investigate population structure using genetic and geographic data simultaneously. Those approaches are often based on computer-intensive stochastic simulations and do not scale with the dimensions of the data sets generated by high-throughput sequencing technologies. There is a growing demand for faster algorithms able to analyse genomewide patterns of population genetic variation in their geographic context. In this study, we present TESS3, a major update of the spatial ancestry estimation program TESS. By combining matrix factorization and spatial statistical methods, TESS3 provides estimates of ancestry coefficients with accuracy comparable to TESS and with run-times much faster than the Bayesian version. In addition, the TESS3 program can be used to perform genome scans for selection, and separate adaptive from nonadaptive genetic variation using ancestral allele frequency differentiation tests. The main features of TESS3 are illustrated using simulated data and analysing genomic data from European lines of the plant species Arabidopsis thaliana.

Predicting Web Service QoS via Combining Matrix Factorization with Network Location

With the increasing abundance of Web Services across Internet, Quality of Service (QoS)based service recommendation has become a hot issue. It is necessary to predict the missing values of QoS for service recommendation. Because Web services run on the Internet, their network locations may be anther critical factor for QoS prediction. Although there have existed many works on QoS prediction, few consider the influence of the network locations of users or Web Services. In this paper, we propose a novel collaborative QoS prediction framework with network location-based regularization (NLBR). We first elaborate the popular Matrix Factorization (MF) model for missing values prediction. Then, by taking advantage of the local connectivity between Web services users, we incorporate network location information to identify the neighborhood. We conduct the experiments on a public large-scale real-world QoS dataset, Experiments show that our proposed approaches have the better prediction performance compared with the existed approaches.