Anomaly detection on attributed networks has received an increasing amount of attention in recent years. Despite the success, most of the existing methods only focus on detecting the abnormal nodes while fail to detect the abnormal subgraphs. In this paper, we define a new problem of hybrid-order anomaly detection on attributed networks, which aims to detect both of the abnormal nodes and subgraphs. To this end, a new deep learning model called Hybrid-Order Graph Attention Network (HO-GAT) is developed, which is able to simultaneously detect the abnormal nodes and motif instances in an attributed network. In order to model the mutual influence between nodes and motif instances, the learning procedures of the node representation and the motif instance representation are integrated into a unified graph attention network with a novel hybrid-order self-attention mechanism. After learning the node representation and the motif instance representation, two decoders are respectively designed to reconstruct the attribute information of the nodes and motif instances, and the hybrid-order topological structure among nodes and motif instances. And finally, the reconstruction errors are utilized as the abnormal score of nodes and motif instances respectively. Extensive experiments conducted on real-world datasets have confirmed the effectiveness of the HO-GAT method.

Academic knowledge graph is an important application of knowledge graph in the vertical field of academia. At present, the construction of the academic knowledge graph is mainly completed by extracting published academic papers, authors, publications, and other information from related databases. However, academic information is not just information of published papers. Scholars’ academic activities include participation in academic conferences, visiting and making presentation, and so on. However, the above academic information is hidden in natural language texts and cannot be directly stored in academic knowledge graph. This article proposes an approach named construct-SCHOLAT knowledge graph to construct an academic event knowledge graph based on academic social network SCHOLAT. The construction framework mainly consists of two parts: data preprocessing and event extraction. In the data preprocessing, we propose a knowledge graph embedding method to represent scholars’ academic social feature. In the event extraction, we concatenate the preprocessed scholar vector with academic we-media blog text into the extraction model based on BiLSTM-CRF fused with attention mechanism. The extracted events are added to academic knowledge graph, and a public relationship exists between the event and the scholar. Compared to the previous methods, our framework has an excellent performance after experimental verification. To the best of our knowledge, this is the first study to use the scholar academic social information of the scholar who edited the text as the event extraction input information. In addition, we publish a Chinese event extraction dataset SCHOLAT academic event extraction.https://www.scholat.com/research/opendata The dataset includes academic we-media blog and the social behavior embedding vector of the scholar. All the data in this dataset are derived from the academic social network SCHOLAT.

Knowledge graphs (KGs) are structured knowledge bases that represent information as a collection of interconnected entities and relations. Link prediction in KGs aims to infer missing or potential links between entities based on triple facts. Among different link prediction methods, knowledge graph embedding (KGE) has gained widespread popularity, with the goal of learning low-dimensional representations for KGs. However, most present KGE methods struggle to capture both local and global neighborhood information efficiently. Additionally, many hybrid methods have limitations in modeling and capturing interactions between triples. In this article, we propose an entity-relation-guided random walk (ERGRW) method for link prediction in KGs. Unlike conventional approaches that solely focus on entity-based walks, ERGRW creatively introduces relations as objects to walk as well. Inspired by distance-based methods, we design novel random walk rules based on the translation principle within triples. Thus, the ERGRW not only captures local and global neighborhood information but also discovers potential semantic relationships and interactions in the KGs. Furthermore, the encoder–decoder framework of ERGRW is able to learn comprehensive representation and improve link prediction performance. Extensive experiments conducted on four standard datasets demonstrate the superiority of ERGRW for link prediction.