Precisely recommending relevant multimedia items from massive candidates to a large number of users is an indispensable yet difficult task on many platforms. A promising way is to project users and items into a latent...
详细信息
ISBN:
(纸本)9781450356572
Precisely recommending relevant multimedia items from massive candidates to a large number of users is an indispensable yet difficult task on many platforms. A promising way is to project users and items into a latent space and recommend items via the inner product of latent factor vectors. However, previous studies paid little attention to the multimedia content itself and couldn't make the best use of preference data like implicit feedback. To fill this gap, we propose a Content-aware Multimedia Recommendation Model with graph autoencoder (graphCAR), combining informative multimedia content with user-item interaction. Specifically, user-item interaction, user attributes and multimedia contents (e.g., images, videos, audios, etc.) are taken as input of the autoencoder to generate the item preference scores for each user. Through extensive experiments on two real-world multimedia Web services: Amazon and Vine, we show that graphCAR significantly outperforms state-of-the-art techniques of both collaborative filtering and content-based methods.
graph clustering aims to discover community structures in networks, the task being fundamentally challenging mainly because the topology structure and the content of the graphs are difficult to represent for clusterin...
详细信息
ISBN:
(纸本)9781450349185
graph clustering aims to discover community structures in networks, the task being fundamentally challenging mainly because the topology structure and the content of the graphs are difficult to represent for clustering analysis. Recently, graph clustering has moved from traditional shallow methods to deep learning approaches, thanks to the unique feature representation learning capability of deep learning. However, existing deep approaches for graph clustering can only exploit the structure information, while ignoring the content information associated with the nodes in a graph. In this paper, we propose a novel marginalized graph autoencoder (MGAE) algorithm for graph clustering. The key innovation of MGAE is that it advances the autoencoder to the graph domain, so graph representation learning can be carried out not only in a purely unsupervised setting by leveraging structure and content information, it can also be stacked in a deep fashion to learn effective representation. From a technical viewpoint, we propose a marginalized graph convolutional network to corrupt network node content, allowing node content to interact with network features, and marginalizes the corrupted features in a graph autoencoder context to learn graph feature representations. The learned features are fed into the spectral clustering algorithm for graph clustering. Experimental results on benchmark datasets demonstrate the superior performance of MGAE, compared to numerous baselines.
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.
Brain functional connectivity (FC) networks inferred from functional magnetic resonance imaging (fMRI) have shown altered or aberrant brain functional connectome in various neuropsychiatric disorders. Recent applicati...
详细信息
Brain functional connectivity (FC) networks inferred from functional magnetic resonance imaging (fMRI) have shown altered or aberrant brain functional connectome in various neuropsychiatric disorders. Recent application of deep neural networks to connectome-based classification mostly relies on traditional convolutional neural networks (CNNs) using input FCs on a regular Euclidean grid to learn spatial maps of brain networks neglecting the topological information of the brain networks, leading to potentially sub-optimal performance in brain disorder identification. We propose a novel graph deep learning framework that leverages non-Euclidean information inherent in the graph structure for classifying brain networks in major depressive disorder (MDD). We introduce a novel graph autoencoder (GAE) architecture, built upon graph convolutional networks (GCNs), to embed the topological structure and node content of large fMRI networks into low-dimensional representations. For constructing the brain networks, we employ the Ledoit-Wolf (LDW) shrinkage method to efficiently estimate high-dimensional FC metrics from fMRI data. We explore both supervised and unsupervised techniques for graph embedding learning. The resulting embeddings serve as feature inputs for a deep fully-connected neural network (FCNN) to distinguish MDD from healthy controls (HCs). Evaluating our model on resting-state fMRI MDD dataset, we observe that the GAE-FCNN outperforms several state-of-the-art methods for brain connectome classification, achieving the highest accuracy when using LDW-FC edges as node features. The graph embeddings of fMRI FC networks also reveal significant group differences between MDD and HCs. Our framework demonstrates the feasibility of learning graph embeddings from brain networks, providing valuable discriminative information for diagnosing brain disorders.
graph representation learning is the foundation for various graph data mining tasks. In the real world, graph data not only contains complex adjacency relationships but also diverse structural information. To address ...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
graph representation learning is the foundation for various graph data mining tasks. In the real world, graph data not only contains complex adjacency relationships but also diverse structural information. To address issues such as overfitting and overemphasis on neighboring information while neglecting structural information in graph autoencoders, a novel approach that combines generative learning and masked autoencoder for graph representation learning is proposed. This method employs a masked autoencoder to mask a portion of the graph structure, using the remaining structure as input to the graph autoencoder, effectively alleviating overfitting. Additionally, leveraging generative learning theory, a new graph autoencoder is introduced, capable of aggregating both neighbor and structural information to generate high-quality graph embeddings. Comparative experiments between GLMAE and representative graph representation learning methods demonstrate that GLMAE achieves state-of-the-art performance in link prediction and node classification tasks.
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.
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.
Location-Based Social Networks (LBSNs) present a significant challenge for inferring social relationships from both social networks and user mobility. While traditional rule-based walk graph representation learning me...
详细信息
ISBN:
(纸本)9783031442223;9783031442230
Location-Based Social Networks (LBSNs) present a significant challenge for inferring social relationships from both social networks and user mobility. While traditional rule-based walk graph representation learning methods predict friendship based on user proximity, they fail to distinguish contributions of different mobile semantics (temporal, spatial, and activity semantics). On the other hand, graph-based autoencoder models have shown promising results, but they are not suitable for heterogeneous information in LBSNs, and they perform poorly when users lack initial features. In this paper, we propose the Social Hypergraph autoencoder (SHGAE) model, a novel autoencoder designed specifically for social hypergraphs formed by LBSNs data, which combines the strengths of these two methods. We initialize nodes vectors via hypergraph-jump-walk embedding strategy to capture features of the hypergraph, then use a well-designed autoencoder with heterogeneous message passing and attention mechanisms to model different semantic node influences. Extensive experiments demonstrate that our model outperforms state-of-the-art methods on the social relationship inference task. Moreover, in the ablation study, we find that our two proposed modules contribute differently to datasets with different sparsity, which can provide valuable insights for future research.
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.
The occurrence of many diseases is associated with miRNA abnormalities. Predicting potential drug-miRNA associations is of great importance for both disease treatment and new drug discovery. Most computation -based ap...
详细信息
The occurrence of many diseases is associated with miRNA abnormalities. Predicting potential drug-miRNA associations is of great importance for both disease treatment and new drug discovery. Most computation -based approaches learn one task at a time, ignoring the information contained in other tasks in the same domain. Multitask learning can effectively enhance the prediction performance of a single task by extending the valid information of related tasks. In this paper, we presented a multitask joint learning framework (MTJL) with a graph autoencoder for predicting the associations between drugs and miRNAs. First, we combined multiple pieces of information to construct a high-quality similarity network of both drugs and miRNAs and then used a graph autoencoder (GAE) to learn their embedding representations separately. Second, to further improve the embedding quality of drugs, we added an auxiliary task to classify drugs using the learned representations. Finally, the embedding representations of drugs and miRNAs were linearly transformed to obtain the predictive association scores between them. A comparison with other state-of-the-art models shows that MTJL has the best prediction performance, and ablation experiments show that the auxiliary task can enhance the embedding quality and improve the robustness of the model. In addition, we show that MTJL has high utility in predicting potential associations between drugs and miRNAs by conducting two case studies.
暂无评论