Xiaomei Bai

Artificial intelligence (AI) is revolutionising scholarly impact evaluation and prediction. By integrating AI and machine learning techniques, researchers can leverage diverse academic networks and multiple sources of academic big data. This integration transforms traditional evaluation methods that rely on structured measurements such as citation counts and journal impact factors, into more comprehensive and objective evaluations. In this paper, we dive deep into latest advancements in scholarly impact evaluation and prediction within the context of AI. We categorize existing models, highlighting their similarities and distinctions, with a particular emphasis on AI-enabled approaches. Building upon the analysis, we discuss the ongoing challenges in scholarly impact research and outline future directions in this field.

Leveraging the multimodal brain signals collected from various electronic devices, such as electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) data, has been regarded as a promising technique for automated brain disease diagnosis. Existing studies on multimodal brain signal analysis mainly focus on data alignment and basic feature integration, yet fail to capture the spatiotemporal correlations amongst diverse signals. This limitation results in the learning of biased brain signal representations. To eliminate this limitation, we propose a novel multimodal Brain Graph Transformer model, named mBGT. By learning both temporal and spatial dynamics exhibited in multiple brain signals, mBGT derives high-quality multimodal representations of brain signals from heterogeneous data sources. Specifically, we construct a dynamic brain graph based on simultaneous EEG-fNIRS data, which effectively embeds the spatiotemporal correlations amongst brain signals. Thereafter, we propose a spatiotemporal information enhanced graph Transformer to encode the constructed brain graph, extensively exploring the functional interactions among different brain regions. Extensive experiments are conducted on a public dataset to demonstrate the advantages of mBGT in terms of the performance in downstream detection tasks, compared to multiple state-of-the-art baselines. These highlight the superiority of mBGT in learning effective representations for brain graphs from multimodal brain signals.

Citation network analysis attracts increasing attention from disciplines of complex network analysis and science of science. One big challenge in this regard is that there are unreasonable citations in citation networks, i.e., cited papers are not relevant to the citing paper. Existing research on citation analysis has primarily concentrated on the contents and ignored the complex relations between academic entities. In this paper, we propose a novel research topic, that is, how to detect anomalous citations. To be specific, we first define anomalous citations and propose a unified framework, named ACTION, to detect anomalous citations in a heterogeneous academic network. ACTION is established based on non-negative matrix factorization and network representation learning, which considers not only the relevance of citation contents but also the relationships among academic entities including journals, papers, and authors. To evaluate the performance of ACTION, we construct three anomalous citation datasets. Experimental results demonstrate the effectiveness of the proposed method. Detecting anomalous citations carry profound significance for academic fairness.

The spread of the Coronavirus disease-2019 epidemic has caused many courses and exams to be conducted online. The cheating behavior detection model in examination invigilation systems plays a pivotal role in guaranteeing the equality of long-distance examinations. However, cheating behavior is rare, and most researchers do not comprehensively take into account features such as head posture, gaze angle, body posture, and background information in the task of cheating behavior detection. In this paper, we develop and present CHEESE, a CHEating detection framework via multiplE inStancE learning. The framework consists of a label generator that implements weak supervision and a feature encoder to learn discriminative features. In addition, the framework combines body posture and background features extracted by 3D convolution with eye gaze, head posture and facial features captured by OpenFace 2.0. These features are fed into the spatio-temporal graph module by stitching to analyze the spatio-temporal changes in video clips to detect the cheating behaviors. Our experiments on three datasets, UCF-Crime, ShanghaiTech and Online Exam Proctoring (OEP), prove the effectiveness of our method as compared to the state-of-the-art approaches, and obtain the frame-level AUC score of 87.58% on the OEP dataset.

Temporal graph learning has attracted great attention with its ability to deal with dynamic graphs. Although current methods are reasonably accurate, most of them are unexplainable due to their black-box nature. It remains a challenge to explain how temporal graph learning models adapt to information evolution. Furthermore, with the increasing application of artificial intelligence in various scientific domains, such as chemistry and biomedicine, the importance of delivering not only precise outcomes but also offering explanations regarding the learning models becomes paramount. This transparency aids users in comprehending the decision-making procedures and instills greater confidence in the generated models. To address this issue, this article proposes a novel physics-informed explainable continual learning (PiECL), focusing on temporal graphs. Our proposed method utilizes physical and mathematical algorithms to quantify the disturbance of new data to previous knowledge for obtaining changed information over time. As the proposed model is based on theories in physics, it can provide a transparent underlying mechanism for information evolution detection, thus enhancing explainability. The experimental results on three real-world datasets demonstrate that PiECL can explain the learning process, and the generated model outperforms other state-of-the-art methods. PiECL shows tremendous potential for explaining temporal graph learning in various scientific contexts.

The spread of the Coronavirus disease-2019 epidemic has caused many courses and exams to be conducted online. The cheating behavior detection model in examination invigilation systems plays a pivotal role in guaranteeing the equality of long-distance examinations. However, cheating behavior is rare, and most researchers do not comprehensively take into account features such as head posture, gaze angle, body posture, and background information in the task of cheating behaviour detection. In this paper, we develop and present CHEESE, a CHEating detection framework via multiplE inStancE learning. The framework consists of a label generator that implements weak supervision and a feature encoder to learn discriminative features. In addition, the framework combines body posture and background features extracted by 3D convolution with eye gaze, head posture and facial features captured by OpenFace 2.0. These features are fed into the spatio-temporal graph module by stitching to analyze the spatio-temporal changes in video clips to detect the cheating behaviors. Our experiments on three datasets, UCF-Crime, ShanghaiTech and Online Exam Proctoring (OEP), prove the effectiveness of our method as compared to the state-of-the-art approaches, and obtain the frame-level AUC score of 87.58% on the OEP dataset.

Graph anomaly detection is a popular and vital task in various real-world scenarios, which has been studied for several decades. Recently, many studies extending deep learning-based methods have shown preferable performance on graph anomaly detection. However, existing methods are lack of efficiency that is definitely necessary for embedded devices. Towards this end, we propose an Efficient Anomaly detection model on heterogeneous Graphs via contrastive LEarning (EAGLE) by contrasting abnormal nodes with normal ones in terms of their distances to the local context. The proposed method first samples instance pairs on meta path-level for contrastive learning. Then, a graph autoencoder-based model is applied to learn informative node embeddings in an unsupervised way, which will be further combined with the discriminator to predict the anomaly scores of nodes. Experimental results show that EAGLE outperforms the state-of-the-art methods on three heterogeneous network datasets.

Knowledge Graphs (KGs) which can encode structural relations connecting two objects with one or multiple related attributes have become an increasingly popular research direction. Given the superiority of deep learning in representing complex data in continuous space, it is handy to represent KGs data, thus promoting KGs construction, representation, and application. This survey article provides a comprehensive overview of deep learning technologies and KGs by exploring research topics from diverse phases of the KGs lifecycle, such as construction, representation, and knowledge-aware application. We propose new taxonomies on these research topics for motivating cross-understanding between deep learning and KGs. Based on the above three phases, we classify the different tasks of KGs and task-related methods. Afterwards, we explain the principles of combing deep learning in various KGs steps like KGs embedding. We further discuss the contribution and advantages of deep learning applied to the different application scenarios. Finally, we summarize some critical challenges and open issues deep learning approaches face in KGs.

Citation network analysis attracts increasing attention from disciplines of complex network analysis and science of science. One big challenge in this regard is that there are unreasonable citations in citation networks, i.e., cited papers are not relevant to the citing paper. Existing research on citation analysis has primarily concentrated on the contents and ignored the complex relations between academic entities. In this paper, we propose a novel research topic, that is, how to detect anomalous citations. To be specific, we first define anomalous citations and propose a unified framework, named ACTION, to detect anomalous citations in a heterogeneous academic network. ACTION is established based on non-negative matrix factorization and network representation learning, which considers not only the relevance of citation contents but also the relationships among academic entities including journals, papers, and authors. To evaluate the performance of ACTION, we construct two anomalous citation datasets. Experimental results demonstrate the effectiveness of the proposed method. Detecting anomalous citations carry profound significance for academic fairness.

With the rapid growth of information technology and sports, a large amount of sports social network data has emerged. Sports social network data contains rich entity information about athletes, coaches, sports teams, football, basketball, and other sports. Understanding the interaction among these entities is meaningful and challenging. To this end, we first introduce the background of sports social networks. Secondly, we review and categorize the recent research efforts in sports social networks and sports social network analysis based on passing networks, from the centrality and its variants to entropy, and several other metrics. Thirdly, we present and compare different sports social network models that have been used for sports social network analysis, modeling, and prediction. Finally, we present promising research directions in the rapidly growing field, including mining the genes of sports team success with multiview learning, evaluating the impact of sports team collaboration with motif‐based graph networks, finding the best collaborative partners in a sports team with attention‐aware graph networks, and finding the rising star for a sports team with attribute‐based convolutional neural networks. This paper aims to provide the researchers with a broader understanding of the sports social networks, especially valuable as a concise introduction for budding researchers interested in this field.