The proliferation of deep learning(DL)has amplified the demand for processing large and complex datasets for tasks such as modeling,classification,and ***,traditional DL methods compromise client privacy by collecting...
详细信息
The proliferation of deep learning(DL)has amplified the demand for processing large and complex datasets for tasks such as modeling,classification,and ***,traditional DL methods compromise client privacy by collecting sensitive data,underscoring the necessity for privacy-preserving solutions like Federated Learning(FL).FL effectively addresses escalating privacy concerns by facilitating collaborative model training without necessitating the sharing of raw *** that FL clients autonomously manage training data,encouraging client engagement is pivotal for successful model *** overcome challenges like unreliable communication and budget constraints,we present ENTIRE,a contract-based dynamic participation incentive mechanism for *** ensures impartial model training by tailoring participation levels and payments to accommodate diverse client *** approach involves several key ***,we examine how random client participation impacts FL convergence in non-convex scenarios,establishing the correlation between client participation levels and model ***,we reframe model performance optimization as an optimal contract design challenge to guide the distribution of rewards among clients with varying participation *** balancing budget considerations with model effectiveness,we craft optimal contracts for different budgetary constraints,prompting clients to disclose their participation preferences and select suitable contracts for contributing to model ***,we conduct a comprehensive experimental evaluation of ENTIRE using three real *** results demonstrate a significant 12.9%enhancement in model performance,validating its adherence to anticipated economic properties.
Stock price prediction is a typical complex time series prediction problem characterized by dynamics,nonlinearity,and *** paper introduces a generative adversarial network model that incorporates an attention mechanis...
详细信息
Stock price prediction is a typical complex time series prediction problem characterized by dynamics,nonlinearity,and *** paper introduces a generative adversarial network model that incorporates an attention mechanism(GAN-LSTM-Attention)to improve the accuracy of stock price ***,the generator of this model combines the Long and Short-Term Memory Network(LSTM),the Attention Mechanism and,the Fully-Connected Layer,focusing on generating the predicted stock *** discriminator combines the Convolutional Neural Network(CNN)and the Fully-Connected Layer to discriminate between real stock prices and generated stock ***,to evaluate the practical application ability and generalization ability of the GAN-LSTM-Attention model,four representative stocks in the United States of America(USA)stock market,namely,Standard&Poor’s 500 Index stock,Apple Incorporatedstock,AdvancedMicroDevices Incorporatedstock,and Google Incorporated stock were selected for prediction experiments,and the prediction performance was comprehensively evaluated by using the three evaluation metrics,namely,mean absolute error(MAE),root mean square error(RMSE),and coefficient of determination(R2).Finally,the specific effects of the attention mechanism,convolutional layer,and fully-connected layer on the prediction performance of the model are systematically analyzed through ablation *** results of experiment show that the GAN-LSTM-Attention model exhibits excellent performance and robustness in stock price prediction.
In the realm of deep learning, Generative Adversarial Networks (GANs) have emerged as a topic of significant interest for their potential to enhance model performance and enable effective data augmentation. This paper...
详细信息
Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the co...
详细信息
Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the computational power of current multi-core systems such as graphics processing units(GPUs)and can reduce the number of communication rounds in distributed training settings. Thus, SGD with large-batch training has attracted considerable attention. However, existing empirical results showed that large-batch training typically leads to a drop in generalization accuracy. Hence, how to guarantee the generalization ability in large-batch training becomes a challenging task. In this paper, we propose a simple yet effective method, called stochastic normalized gradient descent with momentum(SNGM), for large-batch training. We prove that with the same number of gradient computations, SNGM can adopt a larger batch size than momentum SGD(MSGD), which is one of the most widely used variants of SGD, to converge to an?-stationary point. Empirical results on deep learning verify that when adopting the same large batch size,SNGM can achieve better test accuracy than MSGD and other state-of-the-art large-batch training methods.
Deep reinforcement learning(DRL) has demonstrated significant potential in industrial manufacturing domains such as workshop scheduling and energy system ***, due to the model's inherent uncertainty, rigorous vali...
详细信息
Deep reinforcement learning(DRL) has demonstrated significant potential in industrial manufacturing domains such as workshop scheduling and energy system ***, due to the model's inherent uncertainty, rigorous validation is requisite for its application in real-world tasks. Specific tests may reveal inadequacies in the performance of pre-trained DRL models, while the “black-box” nature of DRL poses a challenge for testing model behavior. We propose a novel performance improvement framework based on probabilistic automata,which aims to proactively identify and correct critical vulnerabilities of DRL systems, so that the performance of DRL models in real tasks can be improved with minimal model ***, a probabilistic automaton is constructed from the historical trajectory of the DRL system by abstracting the state to generate probabilistic decision-making units(PDMUs), and a reverse breadth-first search(BFS) method is used to identify the key PDMU-action pairs that have the greatest impact on adverse outcomes. This process relies only on the state-action sequence and final result of each trajectory. Then, under the key PDMU, we search for the new action that has the greatest impact on favorable results. Finally, the key PDMU, undesirable action and new action are encapsulated as monitors to guide the DRL system to obtain more favorable results through real-time monitoring and correction mechanisms. Evaluations in two standard reinforcement learning environments and three actual job scheduling scenarios confirmed the effectiveness of the method, providing certain guarantees for the deployment of DRL models in real-world applications.
Effective management of electricity consumption (EC) in smart buildings (SBs) is crucial for optimizing operational efficiency, cost savings, and ensuring sustainable resource utilization. Accurate EC prediction enabl...
详细信息
In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, faci...
详细信息
In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, facing challenges like task interference, limited adaptability, and difficulty in capturing nuanced linguistic expressions indicative of various conditions. In response to these challenges, our research presents three novel models employing multi-task learning (MTL) to understand mental health behaviors comprehensively. These models encompass soft-parameter sharing-based long short-term memory with attention mechanism (SPS-LSTM-AM), SPS-based bidirectional gated neural networks with self-head attention mechanism (SPS-BiGRU-SAM), and SPS-based bidirectional neural network with multi-head attention mechanism (SPS-BNN-MHAM). Our models address diverse tasks, including detecting disorders such as bipolar disorder, insomnia, obsessive-compulsive disorder, and panic in psychiatric texts, alongside classifying suicide or non-suicide-related texts on social media as auxiliary tasks. Emotion detection in suicide notes, covering emotions of abuse, blame, and sorrow, serves as the main task. We observe significant performance enhancement in the primary task by incorporating auxiliary tasks. Advanced encoder-building techniques, including auto-regressive-based permutation and enhanced permutation language modeling, are recommended for effectively capturing mental health contexts’ subtleties, semantic nuances, and syntactic structures. We present the shared feature extractor called shared auto-regressive for language modeling (S-ARLM) to capture high-level representations that are useful across tasks. Additionally, we recommend soft-parameter sharing (SPS) subtypes-fully sharing, partial sharing, and independent layer-to minimize tight coupling and enhance adaptability. Our models exhibit outstanding performance across various datasets, achieving accuracies of 96.9%, 97.
If adversaries were to obtain quantum computers in the future, their massive computing power would likely break existing security schemes. Since security is a continuous process, more substantial security schemes must...
详细信息
In low-light image enhancement,prevailing Retinex-based methods often struggle with precise illumina-tion estimation and brightness *** can result in issues such as halo artifacts,blurred edges,and diminished details ...
详细信息
In low-light image enhancement,prevailing Retinex-based methods often struggle with precise illumina-tion estimation and brightness *** can result in issues such as halo artifacts,blurred edges,and diminished details in bright regions,particularly under non-uniform illumination *** propose an innovative approach that refines low-light images by leveraging an in-depth awareness of local content within the *** introducing multi-scale effective guided filtering,our method surpasses the limitations of traditional isotropic filters,such as Gaussian filters,in handling non-uniform *** dynamically adjusts regularization parameters in response to local image characteristics and significantly integrates edge perception across different *** balanced approach achieves a harmonious blend of smoothing and detail preservation,enabling more accurate illumination ***,we have designed an adaptive gamma correction function that dynamically adjusts the brightness value based on local pixel intensity,further balancing enhancement effects across different brightness levels in the *** results demonstrate the effectiveness of our proposed method for non-uniform illumination images across various *** exhibits superior quality and objective evaluation scores compared to existing *** method effectively addresses potential issues that existing methods encounter when processing non-uniform illumination images,producing enhanced images with precise details and natural,vivid colors.
Graph similarity learning aims to calculate the similarity between pairs of *** unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation st...
详细信息
Graph similarity learning aims to calculate the similarity between pairs of *** unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation strategies,which can harm the semantic and structural information of graphs and overlook the rich structural information present in *** address these issues,we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive ***,to tackle the problem of random augmentation disrupting the semantics and structure of the graph,we design a learnable augmentation method to selectively choose nodes and edges within the *** enhance contrastive levels,we employ a biased random walk method to generate corresponding subgraphs,enriching the contrastive ***,to solve the issue of previous work not considering multi-level contrastive learning,we utilize graph convolutional networks to learn node representations of augmented views and the original graph and calculate the interaction information between the attribute-augmented and structure-augmented views and the original *** goal is to maximize node consistency between different views and learn node matching between different graphs,resulting in node-level representations for each *** representations are then obtained through pooling operations,and we conduct contrastive learning utilizing both node and subgraph ***,the graph similarity score is computed according to different downstream *** conducted three sets of experiments across eight datasets,and the results demonstrate that the proposed model effectively mitigates the issues of random augmentation damaging the original graph’s semantics and structure,as well as the insufficiency of contrastive ***,the model achieves the best overall performance.
暂无评论