This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs.
Basic knowledge of Python programming and its libraries, as well as a general understanding of the fundamentals of data science and machine learning, will help you grasp the topics covered in this book more easily.
... a novel graph - level anomaly detec- tion method based on the Triple - Unit ... a novel method for graph - level anomaly detection . Extensive experiments verify the ... level. TUAF : Triple - Unit - Based Graph - Level Anomaly Detection 417.
Finding Data Anomalies You Didn't Know to Look For Anomaly detection is the detective work of machine learning: finding the unusual, catching the fraud, discovering strange activity in large and complex datasets.
... a novel graph data augmentation method and employs GIN [32] as encoder to conduct graph-level anomaly detection. However, according to our investigation, graph-level anomaly detection is still under-explored and there are only several ...
This book provides a comprehensive overview of the research on anomaly detection with respect to context and situational awareness that aim to get a better understanding of how context information influences anomaly detection.
... model. The introduction of deep learning brought a series of unsupervised ... Graph Convolutional Networks (GCNs). A novel unsupervised GNN framework was proposed in [14] that uses OCGCN for anomaly detection ... level embedding method to ...
... a novel log anomaly detection model (GLAD-PAW) which performs ... level tasks, e.g. , graph classification , which requires global graph information 68 Y. Wan et al. 2 Related Work 2.1 Log-Based Anomaly Detection 2.2 Graph Neural Networks.