In this paper, we generally formulate the dynamics prediction problem of various network systems (e.g., the prediction of mobility, traffic and topology) as the temporal link prediction task. Different from conventional techniques of temporal link prediction that ignore the potential non-linear characteristics and the informative link weights in the dynamic network, we introduce a novel non-linear model GCN-GAN to tackle the challenging temporal link prediction task of weighted dynamic networks. The proposed model leverages the benefits of the graph convolutional network (GCN), long short-term memory (LSTM) as well as the generative adversarial network (GAN). Thus, the dynamics, topology structure and evolutionary patterns of weighted dynamic networks can be fully exploited to improve the temporal link prediction performance. Concretely, we first utilize GCN to explore the local topological characteristics of each single snapshot and then employ LSTM to characterize the evolving features of the dynamic networks. Moreover, GAN is used to enhance the ability of the model to generate the next weighted network snapshot, which can effectively tackle the sparsity and the wide-value-range problem of edge weights in real-life dynamic networks. To verify the model's effectiveness, we conduct extensive experiments on four datasets of different network systems and application scenarios. The experimental results demonstrate that our model achieves impressive results compared to the state-of-the-art competitors.
FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
University of Electronic Science and Technology of China(电子科技大学);East China Normal University(华东师范大学);University of British Columbia(不列颠哥伦比亚大学);Yale University(耶鲁大学)
Handling Extreme Class Imbalance: Using GANs in Data Augmentation for Suicide Prediction
Management (Harrisburg University of Science \& Technology), Harrisburg, USA;Engineering (Wright State University), Fairborn, USA;Biological Science (Wright State University), Fairborn, USA
针对自杀预测中阳性样本极少导致的极端类别不平衡,本文用 GAN 生成合成数据增强 656 例初始数据集,并比较多种 ML 模型,LR 与 SVM 成功识别唯二测试阳性病例之一。
Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study
ETH Zurich(苏黎世联邦理工学院);University of Zurich(苏黎世大学);Stanford University(斯坦福大学);Stanford Stroke Center(斯坦福中风中心);Institute for Biomedical Engineering(生物医学工程研究所)
OOG- Optuna Optimized GAN Sampling Technique for Tabular Imbalanced Malware Data
Islamic University of Technology(伊斯兰理工大学)
网络空间在现代技术时代占据了人们生活的很大一部分,有利用它的人,也有利用它的人。恶意软件是一种应用程序,其构建不是出于良性目标,它可以伤害,窃取甚至更改个人信息和安全应用程序和软件。因此,有许多技术可以避免恶意软件,其中之一是开发恶意软件的样本,以便系统可以随着越来越多的恶意软件而更新,从而允许它识别恶意软件何时试图进入。生成对抗网络(GAN)采样技术已在这项研究中使用,以生成新的恶意软件样本。GANs有多个变体,为了确定哪个变体对于给定的数据集样本是最佳的,必须修改它们的参数。本研究采用Optuna,一个自主的超参数调整算法,以确定所考虑的数据集的最佳设置。在这项研究中,Optuna Optimized GAN(OOG)方法的架构被显示出来,准确率、精确率、召回率和f1得分分别为98.06%、99.00%、97.23%和98.04%。在调整了XGBoost、LightGBM、CatBoost、Extra Trees Classifier和梯度提升Classifier五种监督提升算法的超参数后,本文的方法还采用了加权集成技术来获得这一结果。除了比较在这一领域的现有努力,该研究表明如何有前途的GAN相比,其他采样技术,如SMOTE。
Modeling Eye Gaze Velocity Trajectories using GANs with Spectral Loss for Enhanced Fidelity
OsloMet – Oslo Metropolitan University(奥斯陆met大学);OsloMet Artificial Intelligence Lab(奥斯陆met人工智能实验室);NordSTAR – Nordic Center for Sustainable and Trustworthy AI Research(北欧可持续和可信AI研究中心);Simula Research Laboratory(simula研究实验室)
Weighted Support Points from Random Measures: An Interpretable Alternative for Generative Modeling
Department of Mathematics and Statistics and Data Sciences, University of Texas at Austin(数学与统计学及数据科学系,德克萨斯大学奥斯汀分校);Department of Probability and Statistics, IIMAS, Universidad Nacional Autónoma de México(概率与统计系,墨西哥国家自治大学)
Generating Synthetic Mobility Networks with Generative Adversarial Networks
Institute of Information Science and Technologies, National Research Council(国家研究委员会信息科学与技术研究所);IMT School for Advanced Studies(IMT高等研究学院);University of Pisa(比萨大学);Free University of Bolzano(博尔扎诺自由大学);University of Trento(特伦托大学);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)
Social-IWSTCNN: A Social Interaction-Weighted Spatio-Temporal Convolutional Neural Network for Pedestrian Trajectory Prediction in Urban Traffic Scenarios
University of Gothenburg(哥德堡大学);Chalmers University of Technology(查尔姆斯理工大学)
Predicting Critical Nodes in Temporal Networks by Dynamic Graph Convolutional Networks
University of Electronic Science and Technology of China(电子科技大学);Nanjing University of Finance and Economics(南京财经大学);University of Nottingham(诺丁汉大学);Sichuan Provincial Key Research Base of Social Science(四川省社会科学重点研究基地);Union Big Data Tech. Inc.(联合大数据技术有限公司)