PageRank Method Research Articles

Revealing the closeness of publication ties in scientific cooperation taking into account scientific productivity based on the Time-Weighted PageRank Method with Citation Intensity

The object of this study is the processes related to the assessment of the closeness of publication ties among scientists and taking into account their productivity related to scientific activity. This is necessary to increase the efficiency of management of research projects. To this end, the PR, TWPR, TWPR-CI methods for calculating scientific productivity estimates of scientists were described. In particular, the TWPR-CI method gives preference to those scientists whose works were more intensively published and cited during the last period of time, which is important for the formation of the composition of the executors of scientific research projects. The method for calculating the closeness of publication ties among scientists or average asymmetric tie strength was also described. The verification of dependence between the evaluation of the closeness of publication ties among scientists and their scientific productivity was carried out based on the analysis of the citation network of scientific publications and the network of scientific cooperation. The networks are built on the basis of the open access Citation Network Dataset (ver. 14). The dataset contains information on more than 5 million scientific publications and more than 36 million citations to them. The correlation analysis revealed the presence of a weak inverse relationship between these estimates. However, the weakness of the connection allows us to state that for this case there is no established correlation between the assessment of scientific productivity and the assessment of the closeness of publication ties. That is, the hypothesis that the weak connection between scientists makes it possible to increase the productivity and innovativeness of their publications was not confirmed. The results allow for a systematic approach to the process of evaluation and planning of the results of research projects, as well as the formation of the composition of their executors

Building Communication Efficient Asynchronous Peer-to-Peer Federated LLMs with Blockchain

Large language models (LLM) have gathered attention with the advent of ChatGPT. However, developing personalized LLM models faces challenges in real-world applications due to data scarcity and privacy concerns. Federated learning addresses these issues, providing collaborative training while preserving the client’s data. Although it has made significant progress, federated learning still faces ongoing challenges, such as communication efficiency, heterogeneous data, and privacy-preserving methods. This paper presents a novel, fully decentralized federated learning framework for LLMs to address these challenges. We utilize different blockchain-federated LLM (BC-FL) algorithms, effectively balancing the trade-off between latency and accuracy in a decentralized-federated learning environment. Additionally, we address the challenge of communication overhead in peer-to-peer networks by optimizing the path for weight transfer and mitigating node anomalies. We conducted experiments to evaluate memory usage and latency in server and serverless environments. Our results demonstrate a decrease in latency by 5X and a 13% increase in accuracy for serverless cases. Comparisons between synchronous and asynchronous scenarios revealed a 76% reduction in information passing time for the latter. The PageRank method is most efficient in eliminating anomalous nodes for better performance of the global federated LLM model. The code is available on GitHub (https://github.com/Sreebhargavibalijaa/Federated_finetuning_LLM-s_p2p_environment)

A Study of Musical Influence Networks and Genre Evolution Based on the Pagerank Approach

The aim of this study is to investigate the definition of musical influence networks and the construction of multilayer directed networks. By analyzing the provided dataset, the parameters of an artist's musical influence were evaluated and a musical influence network was constructed using the Pagerank method. The study also extends the single-layer network parameters to a multilayer network and proposes a centrality measure based on node degree. In terms of genre analysis, the musical eigenvalues of each genre were calculated using MATLAB software and evaluated by a similarity comparison model and an influence comparison model. The results showed that there was a high degree of similarity between certain genres, and the influence of pop/rock music was the most significant. In addition, the changes and relationships of different genres over time were analyzed through multiple spatio-temporal networks, and the results showed that new musical genres have emerged over time, some of which have similar musical characteristics to existing genres.

Infusing external knowledge into user stance detection in social platforms

Stance detection for user reviews on social platforms aims to classify the stance of users’ reviews toward a specific topic. Existing studies focused on the internal semantic features of reviews’ texts, but ignored the external knowledge associated with the review. This paper retrieves external knowledge related to the key information of each review by mapping it to a knowledge graph. Thereafter, this paper infuses the external knowledge into deep learning model for stance detection. Considering that infusing external knowledge may bring noise to the model, this paper adopts the personalized PageRank method to filter the introduced irrelevant external knowledge. Infusing external knowledge can improve the classification performance by providing background knowledge. In addition to considering the textual features of reviews when constructing the stance detection model, this paper employs a gated graph neural network (GGNN) approach to fuse the structural information between reviews to capture the interactions of reviews. The experiments show that the model improves 1.5% –6.9% in macro-average scores compared to six benchmark models in this paper. By combining the textual features and structural information of reviews and introducing external knowledge, the model effectively improves the stance detection performance.

GeneCompete: an integrative tool of a novel union algorithm with various ranking techniques for multiple gene expression data

Background Identifying the genes responsible for diseases requires precise prioritization of significant genes. Gene expression analysis enables differentiation between gene expressions in disease and normal samples. Increasing the number of high-quality samples enhances the strength of evidence regarding gene involvement in diseases. This process has led to the discovery of disease biomarkers through the collection of diverse gene expression data. Methods This study presents GeneCompete, a web-based tool that integrates gene expression data from multiple platforms and experiments to identify the most promising biomarkers. GeneCompete incorporates a novel union strategy and eight well-established ranking methods, including Win-Loss, Massey, Colley, Keener, Elo, Markov, PageRank, and Bi-directional PageRank algorithms, to prioritize genes across multiple gene expression datasets. Each gene in the competition is assigned a score based on log-fold change values, and significant genes are determined as winners. Results We tested the tool on the expression datasets of Hypertrophic cardiomyopathy (HCM) and the datasets from Microarray Quality Control (MAQC) project, which include both microarray and RNA-Sequencing techniques. The results demonstrate that all ranking scores have more power to predict new occurrence datasets than the classical method. Moreover, the PageRank method with a union strategy delivers the best performance for both up-regulated and down-regulated genes. Furthermore, the top-ranking genes exhibit a strong association with the disease. For MAQC, the two-sides ranking score shows a high relationship with TaqMan validation set in all log-fold change thresholds. Conclusion GeneCompete is a powerful web-based tool that revolutionizes the identification of disease-causing genes through the integration of gene expression data from multiple platforms and experiments.

Greedy separation algorithm finding community for a stochastic block model

We propose a greedy separation algorithm that finds the most fitted candidate among stochastic block models for a network, based on three known approaches. The first approach tests whether the network has one or more than two communities based on the distribution of the largest eigenvalue of the adjacency matrix. The second uses the algorithm to infer the classed label of each node in the network. The third approach ascertains the optimal number of clusters using an information criterion based on the Bayesian information criterion. The algorithm combined with the above approaches can find a suitable candidate from successively generated stochastic block models. However, in the second approach, the estimated labels heavily depend on the initial labels. The collection of the hub node and its neighbors is expected to construct one class with the same label. We find the hub nodes and enhance the initial labels by the PageRank method. We also conduct experiments with real data to evaluate the accuracy of the proposed method by comparing it with Markov chain Monte Carlo methods. The greedy separation algorithm with the PageRank method is preferable to the Monte Carlo-based methods.

The Scientific Productivity of Collective Subjects Based on the Time-Weighted PageRank Method with Citation Intensity

This study aims to estimate the scientific productivity of collective subjects. The objective is to build a method for evaluating scientific productivity through calculation, including for new collective subjects with a small citation network—the paper proposes the Time-Weighted PageRank method with citation intensity (TWPR-CI). The Citation Network Dataset (ver. 13) has been analyzed to verify the method. The dataset includes more than 5 million scientific publications and 48 million citations. Four classes of collective subjects (more than 27,000 collective subjects in total) were established. For each class, scientific productivity estimates from 2000 to 2021 were calculated using the PageRank, Time-Weighted PageRank, and TWPR-CI methods. It is shown that the advantage of the TWPR-CI method is the higher sensitivity of the scientific productivity estimates for new collective subjects on average during the first ten years of observation. At the same time, the assessment of scientific productivity for other collective subjects according to this method is stable. However, the small citation network of the new collective subjects prevents the adequate assessment of scientific productivity during the first years of its operation. Therefore, the TWPR-CI method can be used to assess the scientific productivity of collective subjects, in particular the productivity of new ones.

Collective user switching behavior reveals the influence of TV channels and their hidden community structure

Television is the primary medium through which most families access entertainment and information in their daily lives. Thus, understanding users’ TV viewing behavior is meaningful for several practical issues, such as evaluating the influence of TV channels and providing personalized TV recommendations. However, most existing works regarding TV viewing data are limited to basic statistics (e.g., TV ratings). In this paper, we analyze a large-scale TV viewing dataset for a city in China via a complex network approach. We construct a directed network that characterizes the collective channel-switching behavior of viewers. By using the PageRank method, we reveal the influential TV channels that are more in line with people’s expectations than their rankings based on simple TV ratings. We further construct a network in which channels are linked according to their similarity in users’ switching preferences. This network exhibits a clear community structure, which can help TV stations understand which channels are in the bottleneck and which channels have potential. Overall, our work provides a system perspective to evaluate TV channels and their relationships.

A Practical and Sustainable Approach to Determining the Deployment Priorities of Automatic Vehicle Identification Sensors

Monitoring vehicles’ paths is important for the management and governance of smart sustainable cities, where traffic sensors play a significant role. As a typical sensor, an automatic vehicle identification (AVI) sensor can observe the whereabouts and movements of vehicles. In this article, we introduced an indicator called the deployment score to present the deployment priorities of AVIs for a better reconstruction of vehicles’ paths. The deployment score was obtained based on a programming method for maximizing the accuracy of a recurring vehicle’s path and minimizing the number of AVI sensors. The calculation process is data-driven, where a random-work method was developed to simulate massive path data (tracks of vehicles) according to travel characteristics extracted from finite GPS data. Then, for each simulated path, a path-level bi-level programming model (P-BPM) was constructed to find the optimal layout of the AVI sensors. The solutions of the P-BPM proved to be approximate Pareto optima from a data-driven perspective. Furthermore, the PageRank method was presented to integrate the solutions; thus, the deployment score was obtained. The proposed method was validated in Chengdu City, whose results demonstrated the remarkable value of our approach.

Text Classification Model Explainability for Keyword Extraction - Towards Keyword-Based Summarization of Nursing Care Episodes.

Tools to automate the summarization of nursing entries in electronic health records (EHR) have the potential to support healthcare professionals to obtain a rapid overview of a patient's situation when time is limited. This study explores a keyword-based text summarization method for the nursing text that is based on machine learning model explainability for text classification models. This study aims to extract keywords and phrases that provide an intuitive overview of the content in multiple nursing entries in EHRs written during individual patients' care episodes. The proposed keyword extraction method is used to generate keyword summaries from 40 patients' care episodes and its performance is compared to a baseline method based on word embeddings combined with the PageRank method. The two methods were assessed with manual evaluation by three domain experts. The results indicate that it is possible to generate representative keyword summaries from nursing entries in EHRs and our method outperformed the baseline method.

Domain-Specific Keyword Extraction Using Joint Modeling of Local and Global Contextual Semantics

Domain-specific keyword extraction is a vital task in the field of text mining. There are various research tasks, such as spam e-mail classification, abusive language detection, sentiment analysis, and emotion mining, where a set of domain-specific keywords (aka lexicon) is highly effective. Existing works for keyword extraction list all keywords rather than domain-specific keywords from a document corpus. Moreover, most of the existing approaches perform well on formal document corpuses but fail on noisy and informal user-generated content in online social media. In this article, we present a hybrid approach by jointly modeling the local and global contextual semantics of words, utilizing the strength of distributional word representation and contrasting-domain corpus for domain-specific keyword extraction. Starting with a seed set of a few domain-specific keywords, we model the text corpus as a weighted word-graph. In this graph, the initial weight of a node (word) represents its semantic association with the target domain calculated as a linear combination of three semantic association metrics, and the weight of an edge connecting a pair of nodes represents the co-occurrence count of the respective words. Thereafter, a modified PageRank method is applied to the word-graph to identify the most relevant words for expanding the initial set of domain-specific keywords. We evaluate our method over both formal and informal text corpuses (comprising six datasets), and show that it performs significantly better in comparison to state-of-the-art methods. Furthermore, we generalize our approach to handle the language-agnostic case, and show that it outperforms existing language-agnostic approaches.

Identification of critical nodes for cascade faults of grids based on electrical PageRank

In this paper, the electrical PageRank method is proposed to identify the critical nodes in a power grid considering cascading faults as well as directional weighting. This method can rapidly and accurately focus on the critical nodes in the power system. First, the proposed method simulates the scenario in a grid after a node is attacked by cascading faults. The load loss of the grid is calculated. Second, the electrical PageRank algorithm is proposed. The nodal importance of a grid is determined by considering cascading faults as well as directional weights. The electrical PageRank values of the system nodes are obtained based on the proposed electrical PageRank algorithm and ranked to identify the critical nodes in a grid. Finally, the effectiveness of the proposed method is verified using the IEEE39 node system. The proposed method is highly effective in preventing the occurrence of cascading faults in power systems.

A New Discrete Grid-Based Bacterial Foraging Optimizer to Solve Complex Influence Maximization of Social Networks

Influence maximization (IM) is fundamental to social network applications. It aims to find multiple seed nodes with an enormous impact cascade to maximize these nodes’ spread of influence in social networks. Traditional methods for solving influence maximization of the social network, such as the distance method, greedy method, and PageRank method, may suffer from issues of low calculation accuracy and high computational cost. In this paper, we propose a new bacterial foraging optimization algorithm to solve the IM problem based on the complete-three-layer-influence (CTLI) evaluation model. In this algorithm, a novel grid-based reproduction strategy and a direction-adjustment-based chemotaxis strategy are devised to enhance the algorithm’s searchability. Finally, we conduct comprehensive experiments on four social network cases to verify the effectiveness of the proposed algorithm. The experimental results show that our proposed algorithm effectively solves the social network’s influence maximization.

Study and analysis of category based PageRank method

Internet connectivity is now considered to be a basic human right and in this era of information technology, more efficient ways of browsing the web are being found. The most popular search engine, Google uses its ‘Page Rank Algorithm’ for its searches. In this paper, we aim to find out a more efficient way of searching the web and better organising the search result based on the categories of the pages. The results of the proposed algorithm are compared with the existing Page Rank algorithms, which include the original PageRank Algorithm and a Weighted PageRank Algorithm. The results obtained in this paper have been experimentally compared with the data of the above-mentioned algorithms using comparison graphs.

Revealed Comparative Advantage Method for Solving Multicriteria Decision-making Problems

Abstract This study proposes and analyzes a new method for the post-Pareto analysis of multicriteria decision-making (MCDM) problems: the revealed comparative advantage (RCA) assessment method. An interesting feature of the suggested method is that it uses the solution to a special eigenvalue problem and can be considered an analog/modification in the MCDM context of well-known ranking methods including the authority-hub method, PageRank method, and so on, which have been successfully applied to such fields as economics, bibliometrics, web search design, and so on. For illustrative purposes, this study discusses a particular MCDM problem to demonstrate the practicality of the method. The theoretical considerations and conducted calculations reveal that the RCA assessment method is self-consistent and easily implementable. Moreover, comparisons with well-known tools of an MCDM analysis shows that the results obtained using this method are appropriate and competitive. An important particularity of the RCA assessment method is that it can be useful for decision-makers in the case in which no decision-making authority is available or when the relative importance of various criteria has not been preliminarily evaluated.

Overlapping community detection by constrained personalized PageRank

Given a network, local community detection (a.k.a. graph clustering) methods aim at finding communities around the selected initial nodes (also referred to as seeds, starting nodes or core nodes). Methods in this kind successfully address the efficiency problem confronted by global clustering methods. And techniques, such as personalized PageRank and heat kernel diffusion, for ranking the proximity score of vertices nearby with respect to the corresponding starting nodes are developed. However, most of the random-walk based metrics allow a walker to diffuse without any constraint, and the walker can easily run into irrelevant communities. As a result, the corresponding community could include irrelevant high-quality communities (communities with good fitness score) nearby, we refer to the case that a walker goes into irrelevant communities and causes inaccurate expansion of a community as redundant diffusion. In this work, we develop a constrained personalized PageRank method for community expansion to reduce the problem of redundant diffusion. In the mechanism, a walker moves with lower probability to neighbor nodes already in the existing communities, and a walker tends to walk out of the community if the walker walks into an irrelevant community. Extensive experiments on synthetic and large real-world networks demonstrate that the proposed method outperforms approaches in the state of the art by a large margin in accuracy and efficiency.

Neighborhood and PageRank methods for pairwise link prediction

Link prediction is a common problem in network science that cuts across many disciplines. The goal is to forecast the appearance of new links or to find links missing in the network. Typical methods for link prediction use the topology of the network to predict the most likely future or missing connections between a pair of nodes. However, network evolution is often mediated by higher-order structures involving more than pairs of nodes; for example, cliques on three nodes (also called triangles) are key to the structure of social networks, but the standard link prediction framework does not directly predict these structures. To address this gap, in recent work, we propose a new link prediction task called “pairwise link prediction” that directly targets the prediction of new triangles, where one is tasked with finding which nodes are most likely to form a triangle with a given edge. We extend this work in this manuscript, and we evaluate a variety of natural extensions to link prediction methods including neighborhood and PageRank-based methods. A key difference from our previous work is the definition of the neighborhood of an edge, which has a surprisingly large impact on the empirical performance. Our experiments on a variety of networks show that diffusion-based methods are less sensitive to the type of graphs used and more consistent in their results. We also show how our pairwise link prediction framework can be used to get better predictions within the context of standard link prediction evaluation.

USE OF THE LINK RANKING METHOD TO EVALUATE SCIENTIFIC ACTIVITIES OFSCIENTIFIC SPACE SUBJECTS

A modification of the PageRank method based on link ranking is proposed to evaluate the research results of subjects of the scientific space, taking into account self-citation. The method of reducing the influence of self-citation on the final evaluation of the results of research activity of subjects of the scientific space is described. The evaluation of the results of research is calculated using the modified PR-q method, taking into account self-citation as a solution of a system of linear algebraic equations, matrix of which consists of coefficients determined by the number of citations of publications of one scientist in the publications of another scientist. The described method can be used for the task of evaluating the activity of the components of the scientific space: scientists, higher education institutions and their structural units. For the task of evaluating the research activity of subjects of the scientific space, a method based on link ranking (PageRank method for web pages) and taking into account the self-citation of scientists is proposed. The latter allows for an adequate assessment, taking into account the abuses associated with the authors excessive self-citation. The essence of the constructed method lies in the construction of a system of linear algebraic equations, whose coefficients of the matrix reflect the citations of some scientists by others in the citation network of scientific publications. The value of the coefficients of the matrix of such a system of linear algebraic equations is subject to certain restrictions, which allow to reduce the influence of the factor of excessive self-citation of the author on his overall assessment of research activity. The described method can be used to calculate the complex evaluation of the components of the scientific space: the scientist, the institution of higher education and its separate structural units. Evaluating research results provides an opportunity to verify the relevance of the research process to the goals identified at the planning stage and, if necessary, to adjust the progress of those studies. Also, the calculation of research evaluations of the components (objects and entities) of the scientific space is a powerful tool for managing research projects.

The value of PhD in the changing world of work: Traditional and alternative research careers

The paper considers career patterns of researchers and the ways to assess their career achievements on the academic and non-academic labor markets. Taking into account the approaches developed earlier in the framework of the sociology of science, as well as on the basis of recent empirical studies, the authors propose an original approach to the study of a research career, determine the integral indicator of career achievements and assess the research career rank by means of the transition probabilities. The study is based on the data obtained during a survey among Russian researchers involving 828 respondents employed by organizations in the main prospective science and technology areas (academic and non-academic sectors). We suggest the research career achievement (RCA) indicator as an analytical tool for managing highly qualified research personnel. The use of PageRank method enabled to discern an extremely uneven distribution of the research career achievement value in the surveyed sample of researchers. The analysis revealed the main factors determining academic and non-academic research career patterns. The findings attest that the factors affecting career patterns are closely linked with the recognition that the researcher obtains or expects at three levels: individual – professional community – society as a whole.

Forecasting Earthquakes by Hybrid Model of Pattern Informatic and PageRank Methods

Abstract Although there is no proven method for predicting earthquakes in a short time, it is feasible to evaluate their hazards probabilistically. Here, we aim to find active and passive places of Iran’s geographical region. In this regard, we have analyzed pattern informatic (PI) and the relative intensity methods in Iran as retrospective binary forecasting methods, and used the PageRank (PR) algorithm to rank different places. Then, we introduce a hybrid model of PR and PI methods (PR‐PI) for prediction in the earthquakes network. The results show that our method turns out to be one of the most reliable forecasts compared to other methods based on the common relative operating characteristic diagram. We have also found a regional seismogenic map where earthquakes are likely to occur during a specific time interval in the future.