With the rapid development of artificial intelligence (AI) technology and large-scale dataset applications, anomaly subgraph detection is becoming an essential and widespread application. Most existing methods detect anomaly subgraphs depending on the observable anomalous attributes in target data. However, they may face challenges when the target data lacks such anomalous attributes. E.g., identifying suspicious gangs in the target transportation graph solely based on road traffic information, or detecting burst events in nonpublic data without explicit anomalous attributes. To address the detection of implicit anomaly subgraphs (IASs) in such target graphs, this article proposes a novel approach IAS detection (IASD) with multidimensional feature transfer. First, our approach is built upon transfer learning techniques and involves fusing features from multiple graphs. Second, we explore a feature extraction procedure based on a graph attention (GAT) network model to generate representations of anomaly features for large multidimensional attribute graphs. Third, we construct a two-layer graph by introducing an attributed graph referred to as a "source graph," where anomalies can be easily detected, and nodes of the source graph are partially aligned with the target graph. We validate the effectiveness and robustness of IASD through experiments on five real-world datasets, and implement four anomaly subgraph detection tasks in practical applications.

Event detection is a common research topic in visualization. Existing methods always follow an exploration mode, where machine learning algorithms identify events and then analyze them via a visualization system. The detection process does not integrate the expert's experience. In this paper, we propose a novel framework that organizes the original dataset as an integrated graph that allows for Interactive Event Detection (IED) on the graph. Specifically, we formulate the problem Interactive Event Detection as subgraph detection on the graph under expert's interactions. Further, we define a flexible structure called PGraph to model the dataset and then propose an efficient algorithm that returns a subgraph as an event. Our proposed method supports performing various IED tasks under the expert's interactions. We evaluate the utility of our approach by applying it in two scenarios. One uses a social media dataset to study hot events; the other urban burglary dataset is used to detect consecutive burglary cases. Case studies show that our algorithm could detect more global events considering the expert's experience. By quantitative performance experiments, our method outperforms traditional machine detection approaches, especially in the social media dataset; our method's accuracy is higher than baselines at least 10%.

Anomaly detection in multilayer graphs becomes more critical in many application scenarios, i.e., identifying crime hotspots in urban areas by discovering suspicious and illicit behaviors in social networks. However, it is a big challenge to identify anomalies in a layer graph due to the insufficient anomaly features. Most existing methods of anomaly detection determine whether a node is abnormal by looking at the observable anomalous feature values. However, these methods are not suitable for scenarios in which the abnormal features are scarce, e.g., geometric graphs or non-public data in social network services. In this paper, to detect anomaly in a graph with insufficient anomalous features, we propose a pioneering approach ASD-FT (Anomaly Subgraph Detection with Feature Transfer) based on a strategy of anomalous feature transfers between different layers of a multilayer graph. The proposed ASD-FT detects anomaly subgraphs from the graph of the target layer by analyzing the anomalous features in the graph of another layer. We demonstrate the effectiveness and robustness of our approach ASD-FT with extensive experiments on five real-world datasets.