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 n...
详细信息
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.
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 pl...
详细信息
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.
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...
详细信息
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.
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...
详细信息
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.
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 ...
详细信息
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.
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 ...
详细信息
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.
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, retraini...
详细信息
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%.
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 imagin...
详细信息
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.
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 efficienc...
详细信息
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.
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 har...
详细信息
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.
暂无评论