With the development of e-commerce, fraud behaviors have been becoming one biggest threats to e-commerce business. Fraud seriously damage ranking system platforms and adversely influence shopping experience users. It is great practical value detect on platforms. However, task non-trivial, since adversarial action taken by fraudsters. Existing detection systems used in industry easily suffer from performance decay can not adapt upgrade patterns, as they take already known supervision...

Traditional conductive hydrogels have disadvantages for wearable sensors, such as poor electrical conductivity, weak mechanical properties, narrow application temperature range, and required external power supply, which limit their wide application. However, manufacturing hydrogel sensors with excellent properties self-adhesive, temperature-resistant, self-powered remains a challenge. Herein, chitin nanofiber-reinforced eutectogels (CAANF) self-healing, transparent, environment tolerant,...

Predicting the survival of cancer patients holds significant meaning for public health, and has attracted increasing attention in medical information communities. In this study, we propose a novel framework prediction named Multimodal Graph Neural Network (MGNN), which explores features real-world multimodual data such as gene expression, copy number alteration clinical unified framework. order to explore inherent relation, first construct bipartite graphs between multimodal data....

In academia and industries, graph neural networks (GNNs) have emerged as a powerful approach to data processing ranging from node classification link prediction tasks clustering tasks. GNN models are usually handcrafted. However, building handcrafted is difficult requires expert experience because model components complex sensitive variations. The complexity of has brought significant challenges the existing efficiencies GNNs. Hence, many studies focused on automated machine learning...

The interaction of multiple drugs could lead to serious events, which causes injuries and huge medical costs. Accurate prediction drug-drug (DDI) events can help clinicians make effective decisions establish appropriate therapy programs. Recently, many AI-based techniques have been proposed for predicting DDI associated events. However, most existing methods pay less attention the potential correlations between other multimodal data such as targets enzymes. To address this problem, we...

In recent years, cancer patients survival prediction holds important significance for worldwide health problems, and has gained many researchers attention in medical information communities. Cancer can be seen the classification work which is a meaningful challenging task. Nevertheless, research this field still limited. paper, we design novel Multimodal Graph Neural Network (MGNN) framework predicting survival, explores features of real-world multimodal data such as gene expression, copy...

Graph classification has been widely used for knowledge discovery in numerous practical application scenarios, such as social networks and protein-protein interaction networks. Recently, Neural Networks (GNNs), which generalize deep neural to graph-structured data, have drawn considerable attention achieved state-of-the-art performance graph classification. However, existing GNN models mainly focus on capturing the information of immediate or first-order neighboring nodes within a single...

With the emergence of edge computing, a large number devices such as sensor nodes have been deployed in network to sense and process data. However, how provide real-time on-demand energy for these is new challenge issue networks. In real-world applications usually different task burdens due environmental impact, which results dynamic change consumption rate at nodes. Therefore, traditional periodical charging mode cannot meet demand that consumption. this paper, we propose scheduling scheme...

Knowledge graphs (KGs) provide a wealth of prior knowledge for the research on social networks. Cross-lingual entity alignment aims at integrating complementary KGs from different languages and thus benefits various knowledge-driven network studies. Recent methods often take an embedding-based approach to model relation embedding KGs. However, these studies mostly focus information itself its structural features but ignore influence multiple types data in In this paper, we propose new...

Graph Neural Networks (GNNs) have drawn attention due to their excellent performance in fraud detection tasks, which reveal fraudsters by aggregating the features of neighbors. However, some typically tend alleviate suspiciousness connecting with many benign ones. Besides, label-imbalanced neighborhood also deteriorates accuracy. Such behaviors violate homophily assumption and worsen GNN-based detectors. In this paper, we propose a Dual-Augment Network (DAGNN) for tasks. DAGNN, design...

Graph neural networks (GNNs) have received much attention as GNNs recently been successfully applied on non-euclidean data. However, artificially designed graph often fail to get satisfactory model performance for a given architecture search effectively constructs the that achieve expected with rise of automatic machine learning. The challenge is efficiently and automatically getting optimal GNN in vast space. Existing methods serially evaluate architectures, severely limiting system...

Recently, graph neural architecture search (GNAS) frameworks have been successfully used to automatically design the optimal architectures for many problems such as node classification and classification. In existing GNAS frameworks, designed network (GNN) learn representation of homogenous graphs with one type relationship connecting two nodes. However, multi-view graphs, where each view represents a among nodes, are ubiquitous in real world. The traditional without considering interactions...

Drug–drug interaction (DDI) has attracted widespread attention because when incompatible drugs are taken together, DDI will lead to adverse effects on the body, such as drug poisoning or reduced efficacy. The of closely determined by molecular structures involved. To represent data effectively, researchers usually treat structure a molecule graph. Then, previous studies can use handcrafted graph neural network (GNN) model learn representations for prediction. However, in field...