Single-cell ribonucleic acid sequencing (scRNA-seq) allows researchers to study cell heterogeneity and diversity at the individual cell level. Cell clustering is an essential component of scRNA-seq data processing. Ho...
详细信息
Single-cell ribonucleic acid sequencing (scRNA-seq) allows researchers to study cell heterogeneity and diversity at the individual cell level. Cell clustering is an essential component of scRNA-seq data processing. However, the high dimensionality and high noise characteristics of scRNA-seq data may pose problems during data processing. Although many methods are available for scRNA-seq clustering analysis, most of them ignore the topological relationships of scRNA-seq data and do not fully utilize the potential associations between cells. In this study, we present scGAD, a graph attention autoencoder model with a dual decoder structure for clustering scRNA-seq data. We utilize a graph attention autoencoder with two decoders to learn feature representations of cells in latent space. To ensure that the learned latent feature representation maintains node properties and graph structure, we use an inner product decoder and a learnable graph attention decoder to reconstruct graph structure and node properties, respectively. On the 12 real scRNA-seq datasets, the average NMI and ARI scores of scGAD are 0.762 and 0.695, respectively, outperforming state-of-the-art single-cell clustering approaches. Biological analysis shows that the cell labels predicted by scGAD can assist in the downstream analysis of scRNA-seq data.
ABSTRACTPolyline and building simplification remain challenging in cartography. Most proposed algorithms are geometric-based and rely on specific rules. In this study, we propose a deep learning approach to simplify p...
详细信息
ABSTRACTPolyline and building simplification remain challenging in cartography. Most proposed algorithms are geometric-based and rely on specific rules. In this study, we propose a deep learning approach to simplify polylines and buildings based on a graph autoencoder (GAE). The model receives the coordinates of line vertices as inputs and obtains a simplified representation by reconstructing the original inputs with fewer vertices through pooling, in which the graph convolution based on graph Fourier transform is used for the layer-by-layer feature computation. By adjusting the loss functions, constraints such as area and shape preservation and angle-characteristic enhancement are flexibly configured under a unified learning framework. Our results confirmed the applicability of the GAE approach to the multi-scale simplification of land-cover boundaries and contours by adjusting the number of output nodes. Compared with existing Douglas‒Peukcer, Fourier transform, and Delaunay triangulation approaches, the GAE approach was superior in achieving morphological abstraction while producing reasonably low position, area, and shape changes. Furthermore, we applied it to simplify buildings and demonstrated the potential for preserving the diversified characteristics of different types of lines.
Predicting edge weights on graphs has various applications, from transportation systems to social networks. This paper describes a graph Neural Network (GNN) approach for edge weight prediction with guaranteed coverag...
详细信息
Predicting edge weights on graphs has various applications, from transportation systems to social networks. This paper describes a graph Neural Network (GNN) approach for edge weight prediction with guaranteed coverage. We leverage conformal prediction to calibrate the GNN outputs and produce valid prediction intervals. We handle data heteroscedasticity through error reweighting and Conformalized Quantile Regression (CQR). We compare the performance of our method against baseline techniques on real-world transportation datasets. Our approach has better coverage and efficiency than all baselines and showcases robustness and adaptability.
Bitcoin is a decentralized cryptocurrency, which is rapidly growing and offering many advantages. Although its structure protects users from some types of fraud, it is not completely immune, while fraud detection in B...
详细信息
Bitcoin is a decentralized cryptocurrency, which is rapidly growing and offering many advantages. Although its structure protects users from some types of fraud, it is not completely immune, while fraud detection in Bitcoin remains still relatively unexplored. In this paper, we use a graph to model Bitcoin transactions and benefit from the graph’s structure to overcome the lack of informative transaction and user data. We utilize network analysis for feature extraction and model fraud detection as a classification problem using a Deep Neural Network as our classifier. Furthermore, we propose a novel approach that combines a Variational graph autoencoder (VGAE), for deriving appropriate node and graph embeddings, and supervised learning to detect fraudulent Bitcoin transactions. Our experimental results show that the proposed approach, while also affected by high class imbalance, similarly to using only the graph-based features for classification, performs significantly better in detecting high-risk areas in the graph.
As the popularity of cryptocurrencies grows, the threat of phishing scams on trading networks is growing. Detecting unusual transactions within the complex structure of these transaction graphs and imbalanced data bet...
详细信息
As the popularity of cryptocurrencies grows, the threat of phishing scams on trading networks is growing. Detecting unusual transactions within the complex structure of these transaction graphs and imbalanced data between Benign and Scams remains a very important task. In this paper, we present Disentangled Prototypical graph Convolutional autoencoder, which is optimized for detecting anomalies in cryptocurrency transactions. Our model redefines the approach to analyzing cryptocurrency transactions by treating them as edges and accounts as nodes within a graph neural network enhanced by autoencoders. The DP-GCAE model differentiates itself from existing models by implementing disentangled representation learning within its autoencoder framework. This innovative approach allows for a more nuanced capture of the complex interactions within Ethereum transaction graphs, significantly enhancing the ability of the model to discern subtle patterns often obscured in imbalanced datasets. Building upon this, the autoencoder employs a triplet network to effectively disentangle and reconstruct the graph. Reconstruction is used as input to graph Convolutional Network to detect unusual patterns through prototyping. In experiments conducted on real Ethereum transaction data, our proposed DP-GCAE model showed remarkable performance improvements. Compared with existing graph convolution methods, the DP-GCAE model achieved a 37.7 percent point increase in F1 score, validating the effectiveness and importance of incorporating disentangled learning approaches in graph anomaly detection. These advances not only improve the F1-score of identifying phishing scams in cryptocurrency networks, but also provide a powerful framework that can be applied to a variety of graph-based anomaly detection tasks.
We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a con...
详细信息
We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network operating directly on graphs, whose hidden layers are constrained by an autoencoder. Comparing with vanilla graph convolutional networks, the autoencoder step is added to reduce the information loss brought by Laplacian smoothing. We consider applying our model on both homogeneous graphs and heterogeneous graphs. For homogeneous graphs, the autoencoder approximates to the adjacency matrix of the input graph by taking hidden layer representations as encoder and another one-layer graph convolutional network as decoder. For heterogeneous graphs, since there are multiple adjacency matrices corresponding to different types of edges, the autoencoder approximates to the feature matrix of the input graph instead, and changes the encoder to a particularly designed multi-channel pre-processing network with two layers. In both cases, the error occurred in the autoencoder approximation goes to the penalty term in the loss function. In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks. Further, we notice that our technique can be applied on graph attention network to improve the performance as well. This reveals the wide applicability of the proposed autoencoder technique. (c) 2020 Elsevier B.V. All rights reserved.
A responsive consistency retention strategy is crucial for the engineering application of digital twin (DT). The condition monitoring technique based on graph theory can provide an overall reliability assessment and t...
详细信息
A responsive consistency retention strategy is crucial for the engineering application of digital twin (DT). The condition monitoring technique based on graph theory can provide an overall reliability assessment and thus guide DT model updating. However, most existing studies constructed graph topology merely based on data information without incorporating prior engineering knowledge, which restricts the performance of such approaches. To tackle this limitation, a novel graph construction paradigm based on the mechanism of performance degradation and fault propagation is developed in this study. On this basis, unsupervised learning is further combined to forma dynamic spatio-temporal graph based condition monitoring framework for DT consistency retention. Specifically, the spatial dependencies of multi-sensors are quantified based on the evolution of the fault-related frequency band, and then multidomain features are assigned to each graph node. After that, the spatio-temporal graph set is fed to a dual-decoder graph autoencoder to extract the essential features of normal conditions, where a domain adaptation module is introduced to eliminate environmental effects. Hypothesis testing is conducted at last to inspect the machine state over time and make the final decision. Validation and comprehensive comparison experiments were carried out on two engineering scenarios with different scales (component and system level). The Numenta Anomaly Benchmark (NAB) was employed to evaluate the effectiveness of the proposed approach and the results revealed the great potential of the proposed framework for DT consistency retention.
Statistical analysis of extreme events in complex engineering systems is essential for system design and reliability and resilience assessment. Due to the rarity of extreme events and the computational burden of syste...
详细信息
Statistical analysis of extreme events in complex engineering systems is essential for system design and reliability and resilience assessment. Due to the rarity of extreme events and the computational burden of system performance evaluation, estimating the probability of extreme failures is prohibitively expensive. Traditional methods, such as importance sampling, struggle with the high cost of deriving importance sampling densities for numerous components in large-scale systems. Here, we propose a graph learning approach, called importance sampling based on graph autoencoder (GAE-IS), to integrate a modified graph autoencoder model, termed a criticality assessor, with the cross-entropy-based importance sampling method. GAE-IS effectively decouples the criticality of components from their vulnerability to disastrous events in the workflow, demonstrating notable transferability and leading to significantly reduced computational costs of importance sampling in large-scale networks. The proposed methodology improves sampling efficiency by one to two orders of magnitude across several road networks and provides more accurate probability estimations.
The benefits of drug repositioning to the pharmaceutical industry have garnered significant attention in the field of drug development in recent years. Deep learning techniques have significantly improved drug reposit...
详细信息
The benefits of drug repositioning to the pharmaceutical industry have garnered significant attention in the field of drug development in recent years. Deep learning techniques have significantly improved drug repositioning by studying therapeutic drug profiles, diseases, and proteins. As the number of drugs increases, their targets and interactions generate imbalanced data, which may be undesirable as input to computational prediction model. The approach proposed in this paper uses a hierarchical network embedding technique and a graph autoencoder (GAE) scheme to solve this problem. The approach extracts embedding feature vectors of drugs and targets from a heterogeneous multi-source network to predict unknown drug-target interactions (DTIs). We employ a MetaPath instance that has extensive drug and target characteristic data. The effectiveness of utilizing Meta-Path instance, the number of attention heads, and graph Convolutional Network (GCN) and ensemble learning algorithm is analyzed on gold-standard datasets to evaluate the accuracy of the model and validity of the discovered DTI. The results achieved by our model using 10-fold cross-validation testing showed an improvement of 2.52 % in prediction accuracy, 4.2 % in recall, 3.94 % in AUC, and 3.6 % in F-score compared to state-of-theart methods.
The integration of information and communication technologies into modern power systems has contributed to enhanced efficiency, controllability, and voltage regulation. Concurrently, these technologies expose power sy...
详细信息
The integration of information and communication technologies into modern power systems has contributed to enhanced efficiency, controllability, and voltage regulation. Concurrently, these technologies expose power systems to cyberattacks, which could lead to voltage instability and significant damage. Traditional false data injection attacks (FDIAs) detectors are inadequate in addressing cyberattacks on voltage regulation since a) they overlook such attacks within power grids and b) primarily rely on static thresholds and simple anomaly detection techniques, which cannot capture the complex interplay between voltage stability, cyberattacks, and defensive actions. To address the aforementioned challenges, this paper develops an FDIA detection approach that considers data falsification attacks on voltage regulation and enhances the voltage stability index. A graph autoencoder-based detector that is able to identify cyberattacks targeting voltage regulation is proposed. A bi-level optimization approach is put forward to concurrently optimize the objectives of both attackers and defenders in the context of voltage regulation. The proposed detector underwent rigorous training and testing across different kinds of attacks, demonstrating enhanced generalization performance in all situations. Simulations were performed on the Iberian power system topology, featuring 486 buses. The proposed model achieves 98.11% average detection rate, which represents a significant enhancement of 10-25% compared to the cutting-edge detectors. This provides strong evidence for the effectiveness of proposed strategy in tackling cyberattacks on voltage regulation.
暂无评论