检索结果-内蒙古大学图书馆

Asynchronous multimodal PINN pre-train framework based on TransVNet(MPP-TV) and its application in numerical solutions of the Cauchy problem for the Hamilton-Jacobi equation

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2025年 187卷 203-230页

作者： Chen, Tianhao Li, Zeyu Xu, Pengbo Zheng, Haibiao East China Normal Univ Sch Math Sci Key Lab MEA Shanghai Key Lab PMMPMinist Educ Shanghai 200241 Peoples R China Sanda Univ Innovat Res Ctr AI Finance Shanghai 201209 Peoples R China Shanghai Zhangjiang Inst Math Shanghai 201203 Peoples R China

The Hamilton-Jacobi(HJ) equation represents a class of highly nonlinear partial differential equations. Classical numerical techniques, such as finite element methods, face significant challenges when addressing the numerical solutions of such nonlinear HJ equations. However, recent advances in neural network-based approaches, particularly Physics-Informed Neural Networks (PINNs) and neural operator methods, have ushered in innovative paradigms for numerically solving HJ equations. In this work, we leverage the PINN approach, infused with the concept of neural operators. By encoding and extracting features from the discretized images of functions through TransVNet, which is a novel autoencoder architecture proposed in this paper, we seamlessly integrate Hamiltonian information into PINN training, thereby establishing a novel scientific computation framework. Additionally, we incorporate the vanishing viscosity method, introducing viscosity coefficients in our model, which equips our model to tackle potential singularities in nonlinear HJ equations. These attributes signify that our MPP-TV framework paves new avenues and insights for the generalized solutions of nonlinear HJ equations.

关键词： Physics-informed neural network Numerical methods for PDE Hamilton-Jacobi equation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Counterfactual experience augmented off-policy reinforcement learning

引用

NEUROCOMPUTING 2025年 637卷

作者： Lee, Sunbowen Gong, Yicheng Deng, Chao Wuhan Univ Sci & Technol Coll Sci Wuhan 430065 Hubei Peoples R China Wuhan Univ Sci & Technol Hubei Prov Key Lab Syst Sci Met Proc Wuhan 430065 Hubei Peoples R China Wuhan Univ Sci & Technol Intelligent Automobile Engn Res Inst Sch Automobile & Traff Engn Wuhan 430065 Hubei Peoples R China

Reinforcement learning control algorithms face significant challenges due to out-of-distribution and inefficient exploration problems. While model-based reinforcement learning enhances the agent's reasoning and planning capabilities by constructing virtual environments, training such virtual environments can be very complex. In order to build an efficient inference model and enhance the representativeness of learning data, we propose the Counterfactual Experience Augmentation (CEA) algorithm. CEA leverages variational autoencoders to model the dynamic patterns of state transitions and introduces randomness to model non-stationarity. This approach focuses on expanding the learning data in the experience pool through counterfactual inference and performs exceptionally well in environments that follow the bisimulation assumption. Environments with bisimulation properties are usually represented by discrete observation and action spaces, we propose a sampling method based on maximum kernel density estimation entropy to extend CEA to various environments. By providing reward signals for counterfactual state transitions based on real information, CEA constructs a complete counterfactual experience to alleviate the out-of-distribution problem of the learning data, and outperforms general SOTA algorithms in environments with difference properties. Finally, we discuss the similarities, differences and properties of generated counterfactual experiences and real experiences. The code is available at https://***/Aegis1863/CEA.

关键词： Reinforcement learning variational autoencoder Counterfactual inference Bisimulation

来源：评论

学校读者我要写书评

暂无评论

Multi-agent reinforcement learning for cooperative search under aperiodically intermittent communication

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 280卷

作者： Fu, Longyue Wang, Jiao Luo, Hongchen Northeastern Univ Coll Informat Sci & Engn 3-11 Wenhua Rd Shenyang 110819 Liaoning Peoples R China

Aperiodically Intermittent Communication (AIC) refers to the unpredictable irregular disruptions in exchange of information among agents. These disruptions pose significant challenges to multi-agent cooperative search tasks. The challenges are information loss, increased uncertainty, and reduced collaboration efficiency, thus limiting overall search performance. The Aperiodically Intermittent Communication Reinforcement Learning (AICoRL) algorithm is proposed to achieve multi-agent cooperative search under AIC to address these challenges. Firstly, AICoRL integrates an Adaptive Predictive variational autoencoder (AP-VAE) to reconstruct lost information during communication interruptions. Predicting uncertain information through adaptive communication states and global features enables agents to maintain an approximate global perspective. Secondly, to enhance agents' adaptability in complex dynamic environments, the policy network employs multi-agent reinforcement learning with noisy parameterization. It integrates individual observations with reconstructed features and encourages a more diverse exploration of the action space. Extensive experimental results demonstrate that AICoRL significantly outperforms traditional methods in the search task under AIC. Our algorithm achieves higher search efficiency, better reward performance, and stronger robustness. This framework demonstrates its potential for enhancing the performance of multi-agent systems operating under AIC.

关键词： Aperiodically intermittent communication Multi-agent reinforcement learning Multi-agent cooperative search variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

The Application of Lite-GRU Embedding and VAE-Augmented Heterogeneous Graph Attention Network in Friend Link Prediction for LBSNs

引用

APPLIED SCIENCES-BASEL 2025年第8期15卷 4585-4585页

作者： Yang, Ziteng Li, Boyu Wang, Yong Liu, Aoxue China Univ Geosci Wuhan Sch Comp Sci Wuhan 430078 Peoples R China

Friend link prediction is an important issue in recommendation systems and social network analysis. In Location-Based Social Networks (LBSNs), predicting potential friend relationships faces significant challenges due to the diversity of user behaviors, along with the high dimensionality, sparsity, and complex noise in the data. To address these issues, this paper proposes a Heterogeneous Graph Attention Network (GEVEHGAN) model based on Lite Gate Recurrent Unit (Lite-GRU) embedding and variational autoencoder (VAE) enhancement. The model constructs a heterogeneous graph with two types of nodes and three types of edges;combines Skip-Gram and Lite-GRU to learn Point of Interest (POI) and user node embeddings;introduces VAE for dimensionality reduction and denoising of the embeddings;and employs edge-level attention mechanisms to enhance information propagation and feature aggregation. Experiments are conducted on the publicly available Foursquare dataset. The results show that the GEVEHGAN model outperforms other comparative models in evaluation metrics such as AUC, AP, and Top@K accuracy, demonstrating its superior performance in the friend link prediction task.

关键词： friend link prediction gated recurrent unit variational autoencoder heterogeneous graph attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A semi-supervised multiscale generalized-VAE framework for one-class classification

引用

NEUROCOMPUTING 2025年 620卷

作者： Sharma, Renuka Awate, Suyash P. Commonwealth Sci & Ind Res Org CSIRO Data61 Brisbane Australia Indian Inst Technol IIT Bombay Comp Sci & Engn CSE Dept Mumbai India IITB Monash Res Acad Mumbai India

Deep-learning based approaches for unsupervised anomaly detection typically learn either a generative model of the inlier class or a decision boundary to encapsulate the inlier class. In addition to the training data from the inlier class, the availability of a small amount of training data from the outlier class can aid in refining the classifier model using principles of semi-supervised learning. This paper proposes a novel end-to-end deep semi-supervised variational framework for one-class classification of images, leveraging data-adaptive generalized- Gaussian (GG) models leading to effective modeling of distributions in both latent space and image space. The framework proposes a novel variational encoder that models a distribution on a multiscale (here, "scale"refers to spatial resolution) latent-space encoding, together with a generalized reparameterization scheme for the GG model's sampling at each such scale. While the multiscale latent-space helps effective feature learning at coarse and fine spatial scales, the semi-supervision helps tune the feature learning to improve separability between the inliers and the outliers. Results on several publicly available industrial-imaging and medical-imaging datasets show the benefits of our framework's novel components over existing approaches.

关键词： One-class classification variational autoencoder Semi-supervision Multiscale latent space Generalized-Gaussian Robustness Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Industrial multivariate time-series data anomaly detection incorporating attention mechanisms and adversarial training

引用

INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2025年

作者： Yang, Wenjie Chu, Wenchao Wu, Xingfu Zhou, Lianlin Wang, Jiayi Yang, Hua Li, Zirui Hebei Univ Technol Sch Artificial Intelligence State Key Lab Reliabil & Intelligence Elect Equipm Tianjin Peoples R China AECC South Ind Co Ltd Blade Machining Ctr Zhuzhou Peoples R China Hunan Univ Coll Mech & Vehicle Engn Changsha Peoples R China Suzhou Shushe Technol Co Ltd Suzhou Peoples R China Hebei Univ Technol Sch Mech Engn Tianjin Peoples R China

To address the challenges faced in industrial anomaly detection, including data sample imbalance, lack of anomaly labels, and complex spatiotemporal relationships in high-dimensional data, this paper proposes a novel multi-modal time-series anomaly detection model that combines attention mechanisms and adversarial training. In this model, the first step involves utilizing graph attention mechanisms to extract sequence correlation features from multi-modal time-series data, which are then summed with the original data to form a dual-feature-based data representation. Subsequently, a self-supervised learning approach is employed to input this data representation into a variational autoencoder's encoding-decoding network for reconstruction. Anomaly detection is performed by analyzing the error between the input and reconstructed data. The model also employs spatiotemporal attention mechanisms and adversarial training during reconstruction to enhance feature extraction and model generalization. By comparing our proposed model to five commonly used baseline models, we demonstrate its effectiveness in detecting anomalies in scenarios involving high-dimensional data and imbalanced abnormal samples, demonstrating superior anomaly detection performance, as well as excellent performance on real industrial production and processing datasets.

关键词： Anomaly detection deep learning multivariate time series variational autoencoder adversarial learning Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Accelerating Energy Forecasting with Data Dimensionality Reduction in a Residential Environment

引用

ENERGIES 2025年第7期18卷 1637-1637页

作者： Goncalves, Rafael Magalhaes, Diogo Teixeira, Rafael Antunes, Mario Gomes, Diogo Aguiar, Rui L. Inst Telecomunicacoes P-3810193 Aveiro Portugal Univ Aveiro Dept Eletron Telecomunicacoes & Informat P-3810193 Aveiro Portugal

The non-stationary nature of energy data is a serious challenge for energy forecasting methods. Frequent model updates are necessary to adapt to distribution shifts and avoid performance degradation. However, retraining regression models with lookback windows large enough to capture energy patterns is computationally expensive, as increasing the number of features leads to longer training times. To address this problem, we propose an approach that guarantees fast convergence through dimensionality reduction. Using a synthetic neighborhood dataset, we first validate three deep learning models-an artificial neural network (ANN), a 1D convolutional neural network (1D-CNN), and a long short-term memory (LSTM) network. Then, in order to mitigate the long training time, we apply principal component analysis (PCA) and a variational autoencoder (VAE) for feature reduction. As a way to ensure the suitability of the proposed models for a residential context, we also explore the trade-off between low error and training speed by considering three test scenarios: a global model, a local model for each building, and a global model that is fine-tuned for each building. Our results demonstrate that by selecting the optimal dimensionality reduction method and model architecture, it is possible to decrease the mean squared error (MSE) by up to 63% and accelerate training by up to 80%.

关键词： residential energy forecasting machine learning deep learning artificial neural network convolutional neural network long short-term memory dimensionality reduction principal component analysis variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Longitudinal Alzheimer's Disease Progression Prediction With Modality Uncertainty and Optimization of Information Flow

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2025年第1期29卷 259-272页

作者： Dao, Duy-Phuong Yang, Hyung-Jeong Kim, Jahae Ho, Ngoc-Huynh Chonnam Natl Univ Dept Artificial Intelligence Convergence Gwangju 61186 South Korea Chonnam Natl Univ Hosp Dept Nucl Med Gwangju 61469 South Korea

Alzheimer's disease (AD) is a global neurodegenerative disorder that affects millions of individuals worldwide. Actual AD imaging datasets challenge the construction of reliable longitudinal models owing to imaging modality uncertainty. In addition, they are still unable to retain or obtain important information during disease progression from previous to followup time points. For example, the output values of current gates in recurrent models should be close to a specific value that indicates the model is uncertain about retaining or forgetting information. In this study, we propose a model which can extract and constrain each modality into a common representation space to capture intermodality interactions among different modalities associated with modality uncertainty to predict AD progression. In addition, we provide an auxiliary function to enhance the ability of recurrent gate robustly and effectively in controlling the flow of information over time using longitudinal data. We conducted comparative analysis on data from the Alzheimer's Disease Neuroimaging Initiative database. Our model outperformed other methods across all evaluation metrics. Therefore, the proposed model provides a promising solution for addressing modality uncertainty challenges in multimodal longitudinal AD progression prediction.

关键词： Multimodal longitudinal data modality uncertainty variational autoencoder recurrent gate Alzheimer's disease progression

来源：评论

学校读者我要写书评

暂无评论

A 1T1M-based efficient probability storage and computing cell for the VAE-SBN hybrid model

引用

PHYSICA SCRIPTA 2025年第1期100卷

作者： Dai, Yuehua Tan, Su Feng, Zhe Zou, Jianxun Guo, Wenbin Yu, Ruihan Wang, Zeqing Hu, Yang Wang, Haochen Ruan, Hao Hao, Yang Lin, Zhihao Xu, Zuyu Zhu, Yunlai Wu, Zuheng Anhui Univ Sch Integrated Circuits Hefei 230601 Anhui Peoples R China

Bayesian network are crucial components for uncertainty reasoning and knowledge representation in probabilistic graphical models. As model complexity increases, traditional digital methods face challenges in efficiency and resource utilization. In this work, a novel Bayesian network optimization method based on one-transistor one-memristor (1T1M) units for storing and accessing probability values was proposed. This method leverages the sigmoid-like characteristics of 1T1M for computational optimization, integrates probability storage into sigmoid belief network (SBN), and extends to the variational autoencoder (VAE) framework. By storing and manipulating probabilities at hardware level, this approach enhances storage efficiency and access speed while enhancing computational precision and model expressiveness through the sigmoid-like space of 1T1M. Validation experiments using the MNIST digit generation task demonstrate that this method exhibits unique advantages in SBN structures, particularly in handling complex conditional probabilities and inference tasks. Compared to traditional digital implementations, the proposed method exhibits potential advantages in inference speed and hardware utilization.

关键词： memristor probability storage bayesian network sigmoid belief network variational autoencoder image generation

来源：评论

学校读者我要写书评

暂无评论

Identifying local useful information for attribute graph anomaly detection

引用

NEUROCOMPUTING 2025年 617卷

作者： Xi, Penghui Cheng, Debo Lu, Guangquan Deng, Zhenyun Zhang, Guixian Zhang, Shichao Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin Peoples R China Univ South Australia UniSA STEM Adelaide Australia Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China China Univ Min & Technol Sch Comp Sci & Technol Xuzhou Jiangsu Peoples R China

Graph anomaly detection primarily relies on shallow learning methods based on feature engineering and deep learning strategies centred on autoencoder-based reconstruction. However, these methods frequently fail to harness the local attributes and structural information within graph data, making it challenging to capture the underlying distribution in scenarios with class-imbalanced graph anomalies, which can result in overfitting. To deal with the above issue, this paper proposes anew anomaly detection method called LIAD (Identifying Local Useful Information for Attribute Graph Anomaly Detection), which learns the data's underlying distribution and captures richer local information. First, LIAD employs data augmentation techniques to create masked graphs and pairs of positive and negative subgraphs. Then, LIAD leverages contrastive learning to derive rich embedding representations from diverse local structural information. Additionally, LIAD utilizes a variational autoencoder (VAE) to generate new graph data, capturing the neighbourhood distribution within the masked graph. During the training process, LIAD aligns the generated graph data with the original to deepen its comprehension of local information. Finally, anomaly scoring is achieved by comparing the discrimination and reconstruction scores of the contrastive pairs, enabling effective anomaly detection. Extensive experiments on five real-world datasets demonstrate the effectiveness of LIAD compared to state-of-the-art methods. Comprehensive ablation studies and parametric analyses further affirm the robustness and efficacy of our model.

关键词： Graph neural networks Contrastive learning Graph anomaly detection variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：