Collaborative Embedding Research Articles

Unsupervised Feature Selection via Collaborative Embedding Learning

Unsupervised Feature Selection via Collaborative Embedding Learning

Pseudo Labeling Collaborative Embedding Representation: A Multi-Channel GCNs Framework for Semi-Supervised Node Classification

Pseudo Labeling Collaborative Embedding Representation: A Multi-Channel GCNs Framework for Semi-Supervised Node Classification

Self-Attentive Graph Convolution Network With Latent Group Mining and Collaborative Filtering for Personalized Recommendation

The remarkable progress of machine learning has led to some state-of-the-art algorithms in personalized recommendation. Previous recommendation algorithms generally learn users’ and items’ representations based on a user-item rating matrix. However, these methods only consider a user's own preference, but ignore the influence of the user's social circles. In this paper, we propose a novel recommendation algorithm, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Self-Attentive Graph Convolution Network with Latent Group Mining and Collaborative Filtering</i> , which consists of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Latent Group Mining</i> (LGM) module, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Collaborative Embedding</i> (CE) module and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Self-Attentive Graph Convolution</i> (SAGC) module. The LGM module analyzes users’ social circles by exploring their latent groups and generates group embedding for users and items. The CE module uses a graph embedding method to provide semantic collaborative embedding for users and items. The SAGC module fuses users’ (items’) collaborative embedding and group embedding by a self-attentive graph convolution network to learn their fine-grained representations for rating prediction. We conduct experiments on different real-world datasets, which validates that our algorithm outperforms the state-of-the-art algorithms.

Similarity and sparsity collaborative embedding and its application to robust process monitoring

Multivariate measurements in complex industrial processes are commonly contaminated by a number of outliers. In this context, robustness to the corrupted data is an important problem in process monitoring tasks. This paper proposed a novel approach called similarity and sparsity collaborative embedding (SSCE) for efficient robust process monitoring. The proposed SSCE can learn a sparse coefficient matrix by a ℓ1-norm regularization as the sparse constraint on the reconstruction errors, making it robust to the data contaminated by outliers. The similarity preserving matrix is proposed to capture the local structure of the given data, and then the local information is transferred to the sparse coefficients such that the similarity among data points can be preserved. In this way, the reduced-dimensional representations extracted is capable of containing more informative and discriminating characteristics of the original data, which is beneficial to enhance monitoring performance. Meanwhile, projection learning is integrated into the proposed objective function to learn an explicit projection matrix in an overall optimum way, which enables the SSCE to circumvent the out-of-sample problem and facilitate subsequent process monitoring tasks. Two case studies on a simulated typical chemical process and a practical fractionation process demonstrate the effectiveness of the proposed approach.

Few-Shot Learning With Class-Covariance Metric for Hyperspectral Image Classification

Recently, embedding and metric-based few-shot learning (FSL) has been introduced into hyperspectral image classification (HSIC) and achieved impressive progress. To further enhance the performance with few labeled samples, we in this paper propose a novel FSL framework for HSIC with a class-covariance metric (CMFSL). Overall, the CMFSL learns global class representations for each training episode by interactively using training samples from the base and novel classes, and a synthesis strategy is employed on the novel classes to avoid overfitting. During the meta-training and meta-testing, the class labels are determined directly using the Mahalanobis distance measurement rather than an extra classifier. Benefiting from the task-adapted class-covariance estimations, the CMFSL can construct more flexible decision boundaries than the commonly used Euclidean metric. Additionally, a lightweight cross-scale convolutional network (LXConvNet) consisting of 3D and 2D convolutions is designed to thoroughly exploit the spectral-spatial information in the high-frequency and low-frequency scales with low computational complexity. Furthermore, we devise a spectral-prior-based refinement module (SPRM) in the initial stage of feature extraction, which cannot only force the network to emphasize the most informative bands while suppressing the useless ones, but also alleviate the effects of the domain shift between the base and novel categories to learn a collaborative embedding mapping. Extensive experiment results on four benchmark data sets demonstrate that the proposed CMFSL can outperform the state-of-the-art methods with few-shot annotated samples.

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.

Arabic Text Documents Recommendation Using Joint Deep Representations Learning

Although a huge amount of data has been provided on the web to meet different needs of users, it has been more difficult to quickly make satisfactory choices. Therefore, recommender systems have been introduced for offering relevant data and providing users with personalized recommendations. Traditional collaborative based methods modelled efficiently users and items from their rating patterns. By cons, they suffered from the data sparsity problem. As a solution, text user-generated data (e.g., reviews) were useful to provide rich semantic information of user preferences and item features. Seeing that opinions and ratings were complementary, we proposed to fuse them and learn more accurate representations of users and items for recommendation. Unlike Arabic which has received less attention, the majority of methods offered have been focused on English language. It has been represented a fundamental issue in Natural Language Processing (NLP) and artificial intelligence. In this paper, a neural collaborative embedding- and filtering-based approach was proposed for Arabic textual documents recommendation. Due to the recent advances on neural networks, our idea was to couple deep features learning- and deep interaction modelling- based encoders. Indeed, two branches of recurrent neural networks were combined to extract latent features of users and items. Using the generated representations as inputs, deep user-item interactions were captured by stacking multiple layers. This method has proved its efficiency to simultaneously capture the global context and the word frequency information, learn thereafter the obtained high-level latent features and produce final ratings. Extensive experiments on a standard Arabic dataset showed the superiority of our model than state-of-the art methods.

Expression-based prediction of human essential genes and candidate lncRNAs in cancer cells.

Essential genes are required for the reproductive success at either cellular or organismal level. The identification of essential genes is important for understanding the core biological processes and identifying effective therapeutic drug targets. However, experimental identification of essential genes is costly, time consuming and labor intensive. Although several machine learning models have been developed to predict essential genes, these models are not readily applicable to lncRNAs. Moreover, the currently available models cannot be used to predict essential genes in a specific cancer type. In this study, we have developed a new machine learning approach, XGEP (eXpression-based Gene Essentiality Prediction), to predict essential genes and candidate lncRNAs in cancer cells. The novelty of XGEP lies in the utilization of relevant features derived from the TCGA transcriptome dataset through collaborative embedding. When evaluated on the pan-cancer dataset, XGEP was able to accurately predict human essential genes and achieve significantly higher performance than previous models. Notably, several candidate lncRNAs selected by XGEP are reported to promote cell proliferation and inhibit cell apoptosis. Moreover, XGEP also demonstrated superior performance on cancer-type-specific datasets to identify essential genes. The comprehensive lists of candidate essential genes in specific cancer types may be used to guide experimental characterization and facilitate the discovery of drug targets for cancer therapy. The source code and datasets used in this study are freely available at https://github.com/BioDataLearning/XGEP. Supplementary data are available at Bioinformatics online.

Personalized Video Recommendation Using Rich Contents from Videos

Video recommendation has become an essential way of helping people explore the massive videos and discover the ones that may be of interest to them. In the existing video recommender systems, the models make the recommendations based on the user-video interactions and single specific content features. When the specific content features are unavailable, the performance of the existing models will seriously deteriorate. Inspired by the fact that rich contents (e.g., text, audio, motion, and so on) exist in videos, in this paper, we explore how to use these rich contents to overcome the limitations caused by the unavailability of the specific ones. Specifically, we propose a novel general framework that incorporates arbitrary single content feature with user-video interactions, named as collaborative embedding regression (CER) model, to make effective video recommendation in both in-matrix and out-of-matrix scenarios. Our extensive experiments on two real-world large-scale datasets show that CER beats the existing recommender models with any single content feature and is more time efficient. In addition, we propose a priority-based late fusion (PRI) method to gain the benefit brought by the integrating the multiple content features. The corresponding experiment shows that PRI brings real performance improvement to the baseline and outperforms the existing fusion methods.

Deep Collaborative Embedding for information cascade prediction

Recently, information cascade prediction has attracted increasing interest from researchers, but it is far from being well solved partly due to the three defects of the existing works. First, the existing works often assume an underlying information diffusion model, which is impractical in real world due to the complexity of information diffusion. Second, the existing works often ignore the prediction of the infection order, which also plays an important role in social network analysis. At last, the existing works often depend on the requirement of underlying diffusion networks which are likely unobservable in practice. In this paper, we aim at the prediction of both node infection and infection order without requirement of the knowledge about the underlying diffusion mechanism and the diffusion network, where the challenges are two-fold. The first is what cascading characteristics of nodes should be captured and how to capture them, and the second is that how to model the non-linear features of nodes in information cascades. To address these challenges, we propose a novel model called Deep Collaborative Embedding (DCE) for information cascade prediction, which can capture not only the node structural property but also two kinds of node cascading characteristics. We propose an auto-encoder based collaborative embedding framework to learn the node embeddings with cascade collaboration and node collaboration, in which way the non-linearity of information cascades can be effectively captured. The results of extensive experiments conducted on real-world datasets verify the effectiveness of our approach.

Neural Collaborative Embedding From Reviews for Recommendation

This paper mainly studies the personalized rating prediction task based on review texts for the recommendation. Recently, most of the related researches use convolutional neural networks to capture local context information, but it loses word frequency and global context information. In addition, they simply equate the user (item) embedding to review embedding, which brings some irrelevant information of the review text into user preference or item property. Moreover, they only consider the low-order interactions, which remain the fine-grained user-item interactions to be explored. To solve these problems, we propose a novel method neural collaborative embedding model (NCEM). We first adopt pre-trained BERT model, which has been proven to improve most of the downstream NLP tasks, to simultaneously capture the global context and word frequency information. In addition, a self-attention mechanism is introduced to learn the contribution of each review. Next, we develop a neural form of standard factorization machine, which can model first-order and second-order user-item interactions by stacking multiple layers. The extensive experiments on four public datasets showed that NCEM consistently outperforms the state-of-the-art recommendation approaches. Furthermore, the recommendation interpretability can be improved by showing users the high score reviews accompanied recommended item.

Deep Collaborative Embedding for Social Image Understanding.

In this work, we investigate the problem of learning knowledge from the massive community-contributed images with rich weakly-supervised context information, which can benefit multiple image understanding tasks simultaneously, such as social image tag refinement and assignment, content-based image retrieval, tag-based image retrieval and tag expansion. Towards this end, we propose a Deep Collaborative Embedding (DCE) model to uncover a unified latent space for images and tags. The proposed method incorporates the end-to-end learning and collaborative factor analysis in one unified framework for the optimal compatibility of representation learning and latent space discovery. A nonnegative and discrete refined tagging matrix is learned to guide the end-to-end learning. To collaboratively explore the rich context information of social images, the proposed method integrates the weakly-supervised image-tag correlation, image correlation and tag correlation simultaneously and seamlessly. The proposed model is also extended to embed new tags in the uncovered space. To verify the effectiveness of the proposed method, extensive experiments are conducted on two widely-used social image benchmarks for multiple social image understanding tasks. The encouraging performance of the proposed method over the state-of-the-art approaches demonstrates its superiority.