Final Representation Research Articles

User2Vec: A Novel Representation for the Information of the Social Networks for Stock Market Prediction Using Convolutional and Recurrent Neural Networks

Predicting stock market trends is an intriguing and complex problem, which has drawn considerable attention from the research community. In recent years, researchers have employed machine learning techniques to develop prediction models by using numerical market data and textual messages on social networks as their primary sources of information. In this article, we propose User2Vec, a novel approach to improve stock market prediction accuracy, which contributes to more informed investment decision making. User2Vec is a unique method that recognizes the unequal impact of different user opinions on specific stocks, and it assigns weights to these opinions based on the accuracy of their associated social metrics. The User2Vec model begins by encoding each message as a vector. These vectors are then fed into a convolutional neural network (CNN) to generate an aggregated feature vector. Following this, a stacked bi-directional long short-term memory (LSTM) model provides the final representation of the input data over a period. LSTM-based models have shown promising results by effectively capturing the temporal patterns in time series market data. Finally, the output is fed into a classifier that predicts the trend of the target stock price for the next day. In contrast to previous attempts, User2Vec considers not only the sentiment of the messages, but also the social information associated with the users and the text content of the messages. It has been empirically proven that this inclusion provides valuable information for predicting stock direction, thereby significantly enhancing prediction accuracy. The proposed model was rigorously evaluated using various combinations of market data, encoded messages, and social features. The empirical studies conducted on the Dow Jones 30 stock market showed the model’s superiority over existing state-of-the-art models. The findings of these experiments reveal that including social information about users and their tweets, in addition to the sentiment and textual content of their messages, significantly improves the accuracy of stock market prediction.

Understanding Representation Learnability of Nonlinear Self-Supervised Learning

Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, treating the nonlinear neural network as a ``black box". However, the accurate learning results of neural networks are crucial for describing the data distribution features learned by SSL models. Our paper is the first to analyze the learning results of the nonlinear SSL model accurately. We consider a toy data distribution that contains two features: the label-related feature and the hidden feature. Unlike previous linear setting work that depends on closed-form solutions, we use the gradient descent algorithm to train a 1-layer nonlinear SSL model with a certain initialization region and prove that the model converges to a local minimum. Furthermore, different from the complex iterative analysis, we propose a new analysis process which uses the exact version of Inverse Function Theorem to accurately describe the features learned by the local minimum. With this local minimum, we prove that the nonlinear SSL model can capture the label-related feature and hidden feature at the same time. In contrast, the nonlinear supervised learning (SL) model can only learn the label-related feature. We also present the learning processes and results of the nonlinear SSL and SL model via simulation experiments.

C-NTPP: Learning Cluster-Aware Neural Temporal Point Process

Event sequences in continuous time space are ubiquitous across applications and have been intensively studied with both classic temporal point process (TPP) and its recent deep network variants. This work is motivated by an observation that many of event data exhibit inherent clustering patterns in terms of the sparse correlation among events, while such characteristics are seldom explicitly considered in existing neural TPP models whereby the history encoders are often embodied by RNNs or Transformers. In this work, we propose a c-NTPP (Cluster-Aware Neural Temporal Point Process) model, which leverages a sequential variational autoencoder framework to infer the latent cluster each event belongs to in the sequence. Specially, a novel event-clustered attention mechanism is devised to learn each cluster and then aggregate them together to obtain the final representation for each event. Extensive experiments show that c-NTPP achieves superior performance on both real-world and synthetic datasets, and it can also uncover the underlying clustering correlations.

Influence of Work-Life Balance on Job Contentment and Organizational Loyalty in Manufacturing Companies

Work-life balance is accomplishing stability between non-public life and work. Work-existence coordination facilitated work prioritization and remained the right top reputation ideal final representation at work. Many former studies on charismatic management, work-lifestyle balance, job pleasure, and loyalty of organizations, but there are not many studies of charismatic management and work-existence balance. Research on charismatic leadership carried out within the manufacturing enterprise has not often been studied in the last 3 years. Some other distinctions that demarcate this examination from former research are the dimension of job pride variables and the usage of the weiss dimension. Primarily, the study’s objective delivers proof of the influence of charismatic management and work-existence balance on the loyalty of organizations on worker activity pride in manufacturing groups in Indonesia. The research evaluation tool used the Structural Equation version (SEM), with a pattern populace of 250 production corporation fellows in Indonesia. The outcomes that can be concluded from this look at our first, accurate charismatic management will grow worker job contentment, 2nd, a great work-existence stability will boom worker job pride, 1/3, suitable activity pleasure will escalate worker organizational dedication, fourth, charismatic. Management of an awesome work-lifestyle balance will maximize worker organizational loyalty and 5th, amazing work-lifestyle stability does not immediately escalate worker organizational dedication.

A benchmark of computational pipelines for single-cell histone modification data

BackgroundSingle-cell histone post translational modification (scHPTM) assays such as scCUT&Tag or scChIP-seq allow single-cell mapping of diverse epigenomic landscapes within complex tissues and are likely to unlock our understanding of various mechanisms involved in development or diseases. Running scHTPM experiments and analyzing the data produced remains challenging since few consensus guidelines currently exist regarding good practices for experimental design and data analysis pipelines.ResultsWe perform a computational benchmark to assess the impact of experimental parameters and data analysis pipelines on the ability of the cell representation to recapitulate known biological similarities. We run more than ten thousand experiments to systematically study the impact of coverage and number of cells, of the count matrix construction method, of feature selection and normalization, and of the dimension reduction algorithm used. This allows us to identify key experimental parameters and computational choices to obtain a good representation of single-cell HPTM data. We show in particular that the count matrix construction step has a strong influence on the quality of the representation and that using fixed-size bin counts outperforms annotation-based binning. Dimension reduction methods based on latent semantic indexing outperform others, and feature selection is detrimental, while keeping only high-quality cells has little influence on the final representation as long as enough cells are analyzed.ConclusionsThis benchmark provides a comprehensive study on how experimental parameters and computational choices affect the representation of single-cell HPTM data. We propose a series of recommendations regarding matrix construction, feature and cell selection, and dimensionality reduction algorithms.

Compact-Fusion Feature Framework for Ethnicity Classification

In computer vision, ethnicity classification tasks utilize images containing human faces to extract ethnicity labels. Ethnicity is one of the soft biometric feature categories useful in data analysis for commercial, public, and health sectors. Ethnicity classification begins with face detection as a preprocessing process to determine a human’s presence; then, the feature representation is extracted from the isolated facial image to predict the ethnicity class. This study utilized four handcrafted features (multi-local binary pattern (MLBP), histogram of gradient (HOG), color histogram, and speeded-up-robust-features-based (SURF-based)) as the basis for the generation of a compact-fusion feature. The compact-fusion framework involves optimal feature selection, compact feature extraction, and compact-fusion feature representation. The final feature representation was trained and tested with the SVM One Versus All classifier for ethnicity classification. When it was evaluated in two large datasets, UTKFace and Fair Face, the proposed framework achieved accuracy levels of 89.14%, 82.19%, and 73.87%, respectively, for the UTKFace dataset with four or five classes and the Fair Face dataset with four classes. Furthermore, the compact-fusion feature with a small number of features at 4790, constructed based on conventional handcrafted features, achieved competitive results compared with state-of-the-art methods using a deep-learning-based approach.

SAGSleepNet: A deep learning model for sleep staging based on self-attention graph of polysomnography

Sleep is crucial for human health. Automatic sleep stage classification based on polysomnography (PSG) is meaningful for the diagnosis of sleep diseases, which has attracted extensive attention recently. Most existed works learn the representations of PSG based on the conventional grid data structure, ignoring the topological channel correlations among different body regions in non-Euclidean space. To this end, we propose a deep learning model named SAGSleepNet, which transforms PSG into a robust graph structure by neural networks and self-attention mechanism, utilizing graph convolution network (GCN) and bidirectional gated recurrent unit (BiGRU) to capture epoch-level topological channel correlations and sequence-level temporal sleep transitions of PSG, respectively. The final learned representation is fed into a softmax layer to train an end-to-end model for automatic sleep staging. Experimental results on three public datasets (i.e., SleepEDFx, UCD, CAP) show that SAGSleepNet obtains the best classification performance compared with several baselines, including accuracy of 0.807 ,0.765, and 0.746, F1-score of 0.744, 0.750, and 0.695, and Cohen’s Kappa (κ) of 0.721, 0.690, and 0.660. In general, our work provides a reasonable graph structure to model PSG epoch, and makes contribution to explore implicit channel-wise information of PSG by deep learning techniques.

Leveraging Structured Information from a Passage to Generate Questions

Question Generation (QG) is the task of utilizing Artificial Intelligence (Al) technology to generate questions that can be answered by a span of text within a given passage. Existing research on QG in the educational field struggles with two challenges: the mainstream QG models based on seq-to-seq fail to utilize the structured information from the passage; the other is the lack of specialized educational QG datasets. To address the challenges, a specialized QG dataset, reading comprehension dataset from examinations for QG (named RACE4QG), is reconstructed by applying a new answer tagging approach and a data-filtering strategy to the RACE dataset. Further, an end-to-end QG model, which can exploit the intra- and inter-sentence information to generate better questions, is proposed. In our model, the encoder utilizes a Gated Recurrent Units (GRU) network, which takes the concatenation of word embedding, answer tagging, and Graph Attention neTworks(GAT) embedding as input. The hidden states of the GRU are operated with a gated self-attention to obtain the final passage-answer representation, which will be fed to the decoder. Results show that our model outperforms baselines on automatic metrics and human evaluation. Consequently, the model improves the baseline by 0.44, 1.32, and 1.34 on BLEU-4, ROUGE-L, and METEOR metrics, respectively, indicating the effectivity and reliability of our model. Its gap with human expectations also reflects the research potential.

Vision-based fruit recognition via multi-scale attention CNN

Fruit quality assessment, grading and sorting are of vital importance to fruit processing, and all these involve fruit recognition. Vision-based fruit recognition can recognize fruit automatically and further support more applications such as fruit-picking robots, self-checkout service, and dietary guidance. Recent works resort to Convolutional Neural Networks (CNNs) for vision-based fruit recognition because of their powerful expressive capacity. However, most works simply utilize existing CNNs and ignore characteristics of fruit images, resulting in sub-optimal recognition performance. To solve this problem, we adopt a Multi-Scale Attention Network (MSANet), which explores attention from different layers of CNNs and aggregates various visual attentional features from different levels into final comprehensive representations. Extensive evaluations on four fruit benchmark datasets demonstrate that the method achieves state-of-the-art recognition performance. In addition, we report various experimental results from different deep networks as baselines. Codes and models will be released upon publication. Models and code are available at http://123.57.42.89/codes/msanet.html.

TSFN: A Novel Malicious Traffic Classification Method Using BERT and LSTM.

Traffic classification is the first step in network anomaly detection and is essential to network security. However, existing malicious traffic classification methods have several limitations; for example, statistical-based methods are vulnerable to hand-designed features, and deep learning-based methods are vulnerable to the balance and adequacy of data sets. In addition, the existing BERT-based malicious traffic classification methods only focus on the global features of traffic and ignore the time-series features of traffic. To address these problems, we propose a BERT-based Time-Series Feature Network (TSFN) model in this paper. The first is a Packet encoder module built by the BERT model, which completes the capture of global features of the traffic using the attention mechanism. The second is a temporal feature extraction module built by the LSTM model, which captures the time-series features of the traffic. Then, the global and time-series features of the malicious traffic are incorporated together as the final feature representation, which can better represent the malicious traffic. The experimental results show that the proposed approach can effectively improve the accuracy of malicious traffic classification on the publicly available USTC-TFC dataset, reaching an F1 value of 99.50%. This shows that the time-series features in malicious traffic can help improve the accuracy of malicious traffic classification.

A risk identification model for ICT supply chain based on network embedding and text encoding

Public bidding for the information and communication technology (ICT) products offers an external regulatory perspective to identify endogenous risks of ICT supply chain. Owing to the multi-level outsourcing, the modeling methods of the first-order topological similarity are prone to misjudgment. Moreover, only using basic structural attributes (such as enterprise type, registered capital, etc.) is difficult to accurately quantify the enterprise' supply capacity, resulting in the models cannot identify the risky nodes with insufficient supply capacity. In this work, a risk identification Model for ICT supply chain based on Network Embedding and Text Encoding (NETEM) is proposed. In addition to the basic business features of enterprises, the DeepWalk is utilized to obtain the high-order topological representation of the ICT supply chain. Meanwhile, the TextCNN combined with keyword sequence extraction is utilized to supplement text semantic information, and excavate the association between business scope and supply capacity of enterprises. Finally, the basic business features, high-level topological features and text semantic features are spliced to obtain the final enterprise node representation vector, then the node risk classification model is trained. In addition, an ontology is developed for ICT supply chain integration and risk knowledge reuse. The experimental results show that NETEM improves the F1 value of the optimal baseline algorithm by 7.3% on the ICT risk identification data set, and the case study in financial industry demonstrates that the model can be practically applied to identify the risk of supply interruption.

MVContrast: Unsupervised Pretraining for Multi-view 3D Object Recognition

3D shape recognition has drawn much attention in recent years. The view-based approach performs best of all. However, the current multi-view methods are almost all fully supervised, and the pretraining models are almost all based on ImageNet. Although the pretraining results of ImageNet are quite impressive, there is still a significant discrepancy between multi-view datasets and ImageNet. Multi-view datasets naturally retain rich 3D information. In addition, large-scale datasets such as ImageNet require considerable cleaning and annotation work, so it is difficult to regenerate a second dataset. In contrast, unsupervised learning methods can learn general feature representations without any extra annotation. To this end, we propose a three-stage unsupervised joint pretraining model. Specifically, we decouple the final representations into three fine-grained representations. Data augmentation is utilized to obtain pixel-level representations within each view. And we boost the spatial invariant features from the view level. Finally, we exploit global information at the shape level through a novel extract-and-swap module. Experimental results demonstrate that the proposed method gains significantly in 3D object classification and retrieval tasks, and shows generalization to cross-dataset tasks.

Query-based image tagging model using ensemble learning with enhanced artificial bee colony optimization

Digital images make up most multimedia data and are analysed in computer vision applications. Daily uploads of millions of pictures to Internet archives such as satellite image repositories complicate multimedia content and image graphs. As feature vectors, content based image retrieval (CBIR) and image classification models represent high-level image viewpoints. Observing photos recognizes objects and evaluates their significance for image enhancement. To access the visual information of big datasets, efficiently retrieve and query picture graphs. The artificial bee colony (ABC) algorithm is inspired by the foraging behaviour of honeybee swarms. ABC is susceptible to laziness in convergence and local optimums, just like other optimization methods. This study created an enhanced ABC (EABC) model to enhance precision. This study presents query-based image tagging model using ensemble learning with EABC (QbITM-ELEABC) for CBIR for appropriately tagging images based on the query image. We examine a number of convolutional neural network (CNNs) with varying topologies that can be trained on the dataset with varying degrees of similarity. As representations, each network extracts class probability vectors from images. The final image representation is created by combining the ensemble's class probability vectors with image.

Hypercomplex context guided interaction modeling for scene graph generation

Intuitively, humans can consciously and subjectively attend to the interactions between objects, and thus infer reasonable visual relations. However, mainstream approaches of Scene Graph Generation (SGG) strive to alleviate the long-tailed distribution problem with various complicated re-weighting strategies, where a simple concatenation of the refined object features is treated as the final representation of visual relations. In spite of their remarkable progress, such an operation overlooks the importance of interaction on relation recognition. To tackle the problem, this work devises a hyperComplex- Context guided Interaction Modeling (CCIM for short) plug-in, which can be successfully assimilated by the existing methods for performance improvement. Specifically, we first extract the contextual relation feature determined by the constraint relation≈union(head,tail)−headobject−tailobject. Then, we encode the features of relations and objects into hypercomplex space, with three imaginary components, to learn more expressive representations for SGG. Next, guided by the context, we can capture the interaction between a head or tail object and their relation through the Hamilton product. We further reinforce the interaction between enhanced hypercomplex-valued representations of the two entities with Quaternion inner product. At last, the concatenation of all components from the learned hypercomplex feature is adopted as our final relation representation. Extensive experiments on the popular benchmark Visual Genome in various existing approaches demonstrate the effectiveness and generalization of our proposed model-agnostic method under comprehensive evaluation metrics.

Multi-hypothesis representation learning for transformer-based 3D human pose estimation

Despite significant progress, estimating 3D human poses from monocular videos remains a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, we introduce a one-to-many-to-one three-stage framework: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that the proposed method achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. The code and models are available at https://github.com/Vegetebird/MHFormer.

Multi-Behavior Enhanced Heterogeneous Graph Convolutional Networks Recommendation Algorithm based on Feature-Interaction

ABSTRACT Graph convolution neural networks have shown powerful ability in recommendation, thanks to extracting the user-item collaboration signal from users’ historical interaction information. However, many existing studies often learn the final embedded representation of items and users through IDs of user and item, which cannot make well explanation why user choose the item. By making good use of item’s attribute, the networks will gain better interpretability. In this article, we construct a heterogeneous tripartite graph consisting of user-item-feature, and propose the attention interaction graph convolutional neural network recommendation algorithm (ATGCN). We embed multi-feature fusion of users and items into the user feature interaction layer by using multi-head-attention, which explore the user’s potential preference to update the user’s embedded representation. Through the neighborhood aggregation of graph convolution, the feature neighbors’ aggregation of items is constructed to achieve higher-order feature fusions, and the neighborhood aggregation of users and items is carried out on the historical interaction information. Then, the final embedding vector representations of user and item are obtained after many iterations. We verify the effectiveness of our proposed method on three publicly available datasets and ATGCN has improved 1.59%, 2.03%, and 1.27% in normalized discounted cumulative gain (NDCG), Precision and Recall, respectively.

Multi-Modal Fake News Detection via Bridging the Gap between Modals

Multi-modal fake news detection aims to identify fake information through text and corresponding images. The current methods purely combine images and text scenarios by a vanilla attention module but there exists a semantic gap between different scenarios. To address this issue, we introduce an image caption-based method to enhance the model's ability to capture semantic information from images. Formally, we integrate image description information into the text to bridge the semantic gap between text and images. Moreover, to optimize image utilization and enhance the semantic interaction between images and text, we combine global and object features from the images for the final representation. Finally, we leverage a transformer to fuse the above multi-modal content. We carried out extensive experiments on two publicly available datasets, and the results show that our proposed method significantly improves performance compared to other existing methods.

Improving drug response prediction based on two-space graph convolution

Patients with the same cancer types may present different genomic features and therefore have different drug sensitivities. Accordingly, correctly predicting patients’ responses to the drugs can guide treatment decisions and improve the outcome of cancer patients. Existing computational methods leverage the graph convolution network model to aggregate features of different types of nodes in the heterogeneous network. They most fail to consider the similarity between homogeneous nodes. To this end, we propose an algorithm based on two-space graph convolutional neural networks, TSGCNN, to predict the response of anticancer drugs. TSGCNN first constructs the cell line feature space and the drug feature space and separately performs the graph convolution operation on the feature spaces to diffuse similarity information among homogeneous nodes. After that, we generate a heterogeneous network based on the known cell line and drug relationship and perform graph convolution operations on the heterogeneous network to collect the features of different types of nodes. Subsequently, the algorithm produces the final feature representations for cell lines and drugs by adding their self features, the feature space representations, and the heterogeneous space representations. Finally, we leverage the linear correlation coefficient decoder to reconstruct the cell line-drug correlation matrix for drug response prediction based on the final representations. We tested our model on the Cancer Drug Sensitivity Data (GDSC) and Cancer Cell Line Encyclopedia (CCLE) databases. The results indicate that TSGCNN shows excellent performance drug response prediction compared with other eight state-of-the-art methods.

A multi-view-CNN framework for deep representation learning in image classification

Deep representation learning in image classification is an area in computer vision where deep Convolutional Neural Networks (CNNs) have flourished. Nevertheless, developing an efficient image recognition model for real world applications is a challenging task, since image datasets are characterized by instances with a large amount of noise and redundant information. Thus, it is essential to incorporate an intelligent feature extraction and filtering method in order to create robust and efficient image representations. In this work, we propose a Multi-View-CNN framework which drastically boosts the performance of pre-trained CNN models, such as ResNet and VGG in image classification applications. In this approach different type of views of the same initial image are used in order to extract different types of features utilizing pre-trained CNN models. However, in order to reduce the huge dimensional size of the raw CNN’s output features and create a robust image representation, the Principal Component Analysis (PCA) dimension reduction method is applied. Then, all these extracted feature vectors are concatenated building a final composite feature representation of the initial image dataset. Finally, this augmented feature vector is used for training a linear model (Logistic Regression) in order to perform the final classification tasks. The main findings of this work are summarized as follows. First, the proposed Multi-View-CNN framework managed to drastically increase the performance results of pre-trained CNN models. Second, the incorporation of PCA as a final layer into the main CNN topology, instead of using the classical dimension reduction layer components such as Averaging and Max Pooling operations, managed to significantly improve the performance. The whole implementation code of this framework alongside with the datasets used in our experimental simulations was uploaded to our public GitHub repository to the following link: https://github.com/EmmanuelPintelas/A-Multi-View-CNN-Framework-for-Deep-Representation-Learning-in-Image-Classification.

Integration of Multi-Branch GCNs Enhancing Aspect Sentiment Triplet Extraction

Aspect Sentiment Triplet Extraction (ASTE) is a complex and challenging task in Natural Language Processing (NLP). It aims to extract the triplet of aspect term, opinion term, and their associated sentiment polarity, which is a more fine-grained study in Aspect Based Sentiment Analysis. Furthermore, there have been a large number of approaches being proposed to handle this relevant task. However, existing methods for ASTE suffer from powerless interactions between different sources of textual features, and they usually exert an equal impact on each type of feature, which is quite unreasonable while building contextual representation. Therefore, in this paper, we propose a novel Multi-Branch GCN (MBGCN)-based ASTE model to solve this problem. Specifically, our model first generates the enhanced semantic features via the structure-biased BERT, which takes the position of tokens into the transformation of self-attention. Then, a biaffine attention module is utilized to further obtain the specific semantic feature maps. In addition, to enhance the dependency among words in the sentence, four types of linguistic relations are defined, namely part-of-speech combination, syntactic dependency type, tree-based distance, and relative position distance of each word pair, which are further embedded as adjacent matrices. Then, the widely used Graph Convolutional Network (GCN) module is utilized to complete the work of integrating the semantic feature and linguistic feature, which is operated on four types of dependency relations repeatedly. Additionally, an effective refining strategy is employed to detect whether word pairs match or not, which is conducted after the operation of each branch GCN. At last, a shallow interaction layer is designed to achieve the final textual representation by fusing the four branch features with different weights. To validate the effectiveness of MBGCNs, extensive experiments have been conducted on four public and available datasets. Furthermore, the results demonstrate the effectiveness and robustness of MBGCNs, which obviously outperform state-of-the-art approaches.