arXiv subjects

Xiaomei Bai

Publications and source records attributed to Xiaomei Bai.

12 recordsLinked to original sources

arXiv2025

EAGLE: Contrastive Learning for Efficient Graph Anomaly Detection

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.

cs.LG↗

arXiv2024

Multiple Instance Learning for Cheating Detection and Localization in Online Examinations

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.

cs.CV↗

arXiv2020

The Role of Positive and Negative Citations in Scientific Evaluation

Quantifying the impact of scientific papers objectively is crucial for research output assessment, which subsequently affects institution and country rankings, research funding allocations, academic recruitment and national/international scientific priorities. While most of the assessment schemes based on publication citations may potentially be manipulated through negative citations, in this study, we explore Conflict of Interest (COI) relationships and discover negative citations and subsequently weaken the associated citation strength. PANDORA (Positive And Negative COI- Distinguished Objective Rank Algorithm) has been developed, which captures the positive and negative COI, together with the positive and negative suspected COI relationships. In order to alleviate the influence caused by negative COI relationship, collaboration times, collaboration time span, citation times and citation time span are employed to determine the citing strength; while for positive COI relationship, we regard it as normal citation relationship. Furthermore, we calculate the impact of scholarly papers by PageRank and HITS algorithms, based on a credit allocation algorithm which is utilized to assess the impact of institutions fairly and objectively. Experiments are conducted on the publication dataset from American Physical Society (APS) dataset, and the results demonstrate that our method significantly outperforms the current solutions in Recommendation Intensity of list R at top-K and Spearman's rank correlation coefficient at top-K.

cs.DL↗

arXiv2020

Quantifying the Impact of Scholarly Papers Based on Higher-Order Weighted Citations

Quantifying the impact of a scholarly paper is of great significance, yet the effect of geographical distance of cited papers has not been explored. In this paper, we examine 30,596 papers published in Physical Review C, and identify the relationship between citations and geographical distances between author affiliations. Subsequently, a relative citation weight is applied to assess the impact of a scholarly paper. A higher-order weighted quantum PageRank algorithm is also developed to address the behavior of multiple step citation flow. Capturing the citation dynamics with higher-order dependencies reveals the actual impact of papers, including necessary self-citations that are sometimes excluded in prior studies. Quantum PageRank is utilized in this paper to help differentiating nodes whose PageRank values are identical.

cs.DL↗

arXiv2020

An Overview on Evaluating and Predicting Scholarly Article Impact

Scholarly article impact reflects the significance of academic output recognised by academic peers, and it often plays a crucial role in assessing the scientific achievements of researchers, teams, institutions and countries. It is also used for addressing various needs in the academic and scientific arena, such as recruitment decisions, promotions, and funding allocations. This article provides a comprehensive review of recent progresses related to article impact assessment and prediction. The~review starts by sharing some insight into the article impact research and outlines current research status. Some core methods and recent progress are presented to outline how article impact metrics and prediction have evolved to consider integrating multiple networks. Key techniques, including statistical analysis, machine learning, data mining and network science, are discussed. In particular, we highlight important applications of each technique in article impact research. Subsequently, we discuss the open issues and challenges of article impact research. At the same time, this review points out some important research directions, including article impact evaluation by considering Conflict of Interest, time and location information, various distributions of scholarly entities, and rising stars.

cs.DL↗

arXiv2020

Measure the Impact of Institution and Paper via Institution-citation Network

This paper investigates the impact of institutes and papers over time based on the heterogeneous institution-citation network. A new model, IPRank, is introduced to measure the impact of institution and paper simultaneously. This model utilises the heterogeneous structural measure method to unveil the impact of institution and paper, reflecting the effects of citation, institution, and structural measure. To evaluate the performance, the model first constructs a heterogeneous institution-citation network based on the American Physical Society (APS) dataset. Subsequently, PageRank is used to quantify the impact of institution and paper. Finally, impacts of same institution are merged, and the ranking of institutions and papers is calculated. Experimental results show that the IPRank model better identifies universities that host Nobel Prize laureates, demonstrating that the proposed technique well reflects impactful research.

cs.DL↗

arXiv2020

Author Impact: Evaluations, Predictions, and Challenges

Author impact evaluation and prediction play a key role in determining rewards, funding, and promotion. In this paper, we first introduce the background of author impact evaluation and prediction. Then, we review recent developments of author impact evaluation, including data collection, data pre-processing, data analysis, feature selection, algorithm design, and algorithm evaluation. Thirdly, we provide an in-depth literature review on author impact predictive models and common evaluation metrics. Finally, we look into the representative research issues, including author impact inflation, unified evaluation standards, academic success gene, identification of the origins of hot streaks, and higher-order academic networks analysis. This paper should help the researchers obtain a broader understanding in author impact evaluation and prediction, and provides future research directions.

cs.DL↗

arXiv2020

Quantifying Success in Science: An Overview

Quantifying success in science plays a key role in guiding funding allocations, recruitment decisions, and rewards. Recently, a significant amount of progresses have been made towards quantifying success in science. This lack of detailed analysis and summary continues a practical issue. The literature reports the factors influencing scholarly impact and evaluation methods and indices aimed at overcoming this crucial weakness. We focus on categorizing and reviewing the current development on evaluation indices of scholarly impact, including paper impact, scholar impact, and journal impact. Besides, we summarize the issues of existing evaluation methods and indices, investigate the open issues and challenges, and provide possible solutions, including the pattern of collaboration impact, unified evaluation standards, implicit success factor mining, dynamic academic network embedding, and scholarly impact inflation. This paper should help the researchers obtaining a broader understanding of quantifying success in science, and identifying some potential research directions.

cs.DL↗

arXiv2020

Predicting the Citations of Scholarly Paper

Citation prediction of scholarly papers is of great significance in guiding funding allocations, recruitment decisions, and rewards. However, little is known about how citation patterns evolve over time. By exploring the inherent involution property in scholarly paper citation, we introduce the Paper Potential Index (PPI) model based on four factors: inherent quality of scholarly paper, scholarly paper impact decaying over time, early citations, and early citers' impact. In addition, by analyzing factors that drive citation growth, we propose a multi-feature model for impact prediction. Experimental results demonstrate that the two models improve the accuracy in predicting scholarly paper citations. Compared to the multi-feature model, the PPI model yields superior predictive performance in terms of range-normalized RMSE. The PPI model better interprets the changes in citation, without the need to adjust parameters. Compared to the PPI model, the multi-feature model performs better prediction in terms of Mean Absolute Percentage Error and Accuracy; however, their predictive performance is more dependent on the parameter adjustment.

cs.DL↗

arXiv2020

Implicit Multi-feature Learning for Dynamic Time Series Prediction of the Impact of Institutions

Predicting the impact of research institutions is an important tool for decision makers, such as resource allocation for funding bodies. Despite significant effort of adopting quantitative indicators to measure the impact of research institutions, little is known that how the impact of institutions evolves in time. Previous researches have focused on using the historical relevance scores of different institutions to predict potential future impact for these institutions. In this paper, we explore the factors that can drive the changes of the impact of institutions, finding that the impact of an institution, as measured by the number of the accepted papers of the institution, more is determined by the authors' influence of the institution. Geographic location of institution feature and state GDP can drive the changes of the impact of institutions. Identifying these features allows us to formulate a predictive model that integrates the effects of individual ability, location of institution, and state GDP. The model unveils the underlying factors driving the future impact of institutions, which can be used to accurately predict the future impact of institutions.

cs.SI↗

arXiv2020

Scientific Paper Recommendation: A Survey

Globally, recommendation services have become important due to the fact that they support e-commerce applications and different research communities. Recommender systems have a large number of applications in many fields including economic, education, and scientific research. Different empirical studies have shown that recommender systems are more effective and reliable than keyword-based search engines for extracting useful knowledge from massive amounts of data. The problem of recommending similar scientific articles in scientific community is called scientific paper recommendation. Scientific paper recommendation aims to recommend new articles or classical articles that match researchers' interests. It has become an attractive area of study since the number of scholarly papers increases exponentially. In this survey, we first introduce the importance and advantages of paper recommender systems. Second, we review the recommendation algorithms and methods, such as Content-Based methods, Collaborative Filtering methods, Graph-Based methods and Hybrid methods. Then, we introduce the evaluation methods of different recommender systems. Finally, we summarize open issues in the paper recommender systems, including cold start, sparsity, scalability, privacy, serendipity and unified scholarly data standards. The purpose of this survey is to provide comprehensive reviews on scholarly paper recommendation.

cs.IR↗

arXiv2019

Graduate Employment Prediction with Bias

The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students' employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework.

cs.LG↗