Social perception recommendation systems can effectively alleviate the user cold start problem by leveraging the side information of social networks. However, most social perception recommendation systems treat user r...
详细信息
Robots with very weak capabilities placed on the vertices of a graph are required to move toward a common vertex from where they do not move anymore. The task is known as the Gathering problem and it has been extensiv...
详细信息
ISBN:
(纸本)9783031744976;9783031744983
Robots with very weak capabilities placed on the vertices of a graph are required to move toward a common vertex from where they do not move anymore. The task is known as the Gathering problem and it has been extensively studied in the last decade with respect to both general graphs and specific topologies. Most of the challenges faced are due to possible isometries observable from the placement of the robots with respect to the underlying topology. Rings, Grids, Complete graphs are just a few examples of very regular topologies where the placement of the robots and suitable movements are crucial for succeeding in Gathering. Here we are interested in understanding what can be done in Butterfly graphs where really many isometries are present and most importantly unavoidable by any movement. We propose a Gathering algorithm for the so-called leader configurations, i.e., those where the initial placement of the robots admits the detection (and election) of one robot as the leader. We introduce a non-trivial technique to elect the leader which is of its own interest. We also prove that the proposed Gathering algorithm is asymptotically optimal in terms of synchronous rounds required.
Since the pandemic, drug repurposing has become a helpful technique for associating treatments to new or already known diseases. Drug repurposing finds new uses for existing drugs, leading to a more affordable solutio...
详细信息
ISBN:
(纸本)9798350384734;9798350384727
Since the pandemic, drug repurposing has become a helpful technique for associating treatments to new or already known diseases. Drug repurposing finds new uses for existing drugs, leading to a more affordable solution than de novo drug development. The reduction in time and costs that drug repurposing provides makes it an effective technique to accelerate the process of discovering new treatments. In the present study, we apply a graph deep learning approach to a heterogeneous biomedical graph, aiming to predict a specific link type that connects diseases with drugs, in order to put forward drug repurposing opportunities. In particular, we generate a new model called DRAGON, which builds upon a two-layered Graph Neural Network pipeline. In the encoder stage, drug and protein nodes arc initialized with embeddings representing molecular structure and amino acid sequence information. We compare the proposed model to previous baselines that studied the disease drug prediction approach but did not consider the initialization with embeddings of these two node types. DRAGON reports an improvement of 0.02 in the area under the precision-recall curve when compared to these baselines. We hypothesize that the repurposing model may benefit from the inclusion of multimodal information from different sources.
Cyberattacks, especially Botnet distributed Denial of Service (DDoS), increasingly target networked systems, compromise interconnected nodes by constantly spreading malware. In order to prevent these attacks in their ...
详细信息
ISBN:
(纸本)9798331531317;9798331531300
Cyberattacks, especially Botnet distributed Denial of Service (DDoS), increasingly target networked systems, compromise interconnected nodes by constantly spreading malware. In order to prevent these attacks in their early stages, which includes stopping the spread of malware, it is vital to identify compromised nodes and successfully predict potential attack paths. To this end, this paper proposes a novel system based on an Associated Random Neural Network (ARNN) that simultaneously detects intrusion at the network-level and estimates the network attack graph. In this system, ARNN is trained online to minimize problem-specific multi-task loss so that it identifies compromised network nodes, while the neural network connection weights also estimate the attack path. The performance of the method is calculated using the Kitsune attack dataset, showing that the method achieves a recall rate above 0.95 in estimating the network attack graph, and provides a near-perfect classification of compromised nodes. The ARNN-based system for dynamic and continuous estimation of compromised nodes and network attack graphs, can pave the way for enhancing security measures, and stopping Botnet DDoS attacks from spreading in networked systems.
distributednetworks and systems are becoming more and more widespread and practical in applications. The distributed network has a large scale and a large number of edge terminals, which generate massive data during ...
详细信息
distributednetworks and systems are becoming more and more widespread and practical in applications. The distributed network has a large scale and a large number of edge terminals, which generate massive data during operation. As far as fault diagnosis is concerned, traditional techniques face many challenges. The paper proposes a Fault Diagnosis Method Based on distributed Online Collaborative Distillation (DOCD) for distributed and decentralized scenes. To adapt to the large-scale distributed network and the unstable communication quality scenario, the method distributes the training tasks among the terminal nodes to eliminate the strong dependence of each terminal on the cloud server. Each terminal processes the local data separately and trains the fault diagnosis model locally. Through online optimized collaborative distillation, each terminal model exchanges information and knowledge to improve the diagnostic capability of global data. Finally, the effectiveness of the proposed method is proved by experiments.
In distributed computing, questions of computability are exquisitely sensitive to minute details of the model assumptions, and there is no universally agreed upon model of network computing. Here, we study which funct...
详细信息
Cervical cancer remains a critical global health issue, necessitating more accurate diagnostic techniques for effective management. Traditional methods, which rely heavily on human analysis of cervicography images, ar...
详细信息
ISBN:
(纸本)9798350384734;9798350384727
Cervical cancer remains a critical global health issue, necessitating more accurate diagnostic techniques for effective management. Traditional methods, which rely heavily on human analysis of cervicography images, are hampered by significant limitations such as variability in interpretation and a shortage of specialists, especially in low- and middle-income countries. This study introduces an advanced approach using a convolutional neural network (CNN), specifically the DenseNet121 architecture, to enhance the classification accuracy of cervical intraepithelial neoplasia (CIN) and normal cervix cases. We employed robust k-fold cross-validation on images sourced from the international Agency for Research on Cancer (IARC) to train and refine our model. Subsequent testing on a separate dataset from "Hospital Zambrano Hellion, Tec Salud" allowed us to evaluate the model's effectiveness in a real-world clinical setting. The results indicate promising improvements in diagnostic accuracy, suggesting that the CNN-based approach could significantly enhance the current methods used for cervical cancer screening and diagnosis.
Deployment for underwater sensor networks (UWSNs) is one of the key issues for the topology management, which determines the overall network coverage and profoundly affects the network data collection performance. Thi...
详细信息
ISBN:
(纸本)9798350350227;9798350350210
Deployment for underwater sensor networks (UWSNs) is one of the key issues for the topology management, which determines the overall network coverage and profoundly affects the network data collection performance. This paper proposes a distributed energy-efficient self-adjusting UWSN deployment algorithm with the full consideration of the UWSN application scenarios, which includes two phases. In the initial deployment phase, the nodes at different positions will be assigned differential initial energy levels in different methods in accordance with the subsequent routing principles. During the redeployment phase, based on the virtual force theory, nodes will adjust their positions in a distributed way considering their neighbor nodes' positions, as well as the area and layer boundaries. Through the simulation experiments, the proposed algorithm can effectively improve the network coverage performance and significantly benefit the network routing process compared with the benchmark UWSN self-adjusting deployment algorithms.
As the scale of data continues to grow, the training of machine learning models presents new challenges. In this paper, a machine learning model is established, which is optimized by stochastic gradient descent algori...
详细信息
Temporal Graph Neural networks (TGNNs) have achieved success in real-world graph-based applications. The increasing scale of dynamic graphs necessitates distributed training. However, deploying TGNNs in a distributed ...
详细信息
ISBN:
(纸本)9789819757787;9789819757794
Temporal Graph Neural networks (TGNNs) have achieved success in real-world graph-based applications. The increasing scale of dynamic graphs necessitates distributed training. However, deploying TGNNs in a distributed setting poses challenges due to the temporal dependencies in dynamic graphs, the need for computation balance during distributed training, and the non-ignorable communication costs across disjointed trainers. In this paper, we propose DisTGL, a distributed temporal graph neural network learning system. Leveraging a temporal-aware partitioning scheme and a series of enhanced communication techniques, DisTGL ensures efficient distributed computation and minimizes communication overhead. Based on that, DisTGL facilitates fast TGNN training and downstream tasks. An evaluation of DisTGL using various TGNN models shows that i) DisTGL achieves acceleration of up to 10x compared to existing TGNN frameworks;and ii) the proposed distributed dynamic graph partitioning reduces cross-machine operations by 25%, while the optimized communication reduce the costs by 1.5-2.5x.
暂无评论