Citation Graph Research Articles

Introducing new node prediction in graph mining: Predicting all links from isolated nodes with Graph Neural Networks

This paper introduces new node prediction, a fresh problem in the field of graph mining and social network analysis. This task can be categorized as zero-shot out-of-graph all-links prediction, and aims to predict all links coming from or going to a new, isolated, and unobserved node that was previously disconnected from the graph. In comparison with classic approaches to link prediction (including few-shot out-of-graph link prediction), this problem bears two key differences: (1) the new node has no existing links from which to extract patterns for new predictions; and (2) the goal is to predict not just one, but all the links of this new node, or, at least, a significant part of them. Experiments used an architecture based on Deep Graph Neural Networks, and were carried out on two datasets: a bibliographic citation graph and a drug–drug interaction graph. Results demonstrate that this challenging problem can be solved satisfactorily by using state-of-the-art Deep Learning techniques.

The Journal of Law and Society in context: a bibliometric analysis

AbstractOn this, the occasion of its 50th anniversary, we employ a quantitative analysis of the Journal of Law and Society (JLS) to chart empirically the evolution of socio‐legal studies in the United Kingdom (UK). By tracing the influence(s) of the JLS upon the development of UK socio‐legal research, not only do we demonstrate a new mode of exploring knowledge production in the field of socio‐legal studies, but we also illustrate how computational methods can augment hermeneutical approaches to mapping socio‐legal trends. Through (a blend of) three different analytical approaches – descriptive analyses of bibliographic metadata, text‐linguistic analyses of a corpus of full‐text articles, and network analyses of citation graphs – we generate comparative information about the JLS since its inception in 1974. We then employ this data to interrogate the JLS’ own narratives; using predictions, ambitions, and statements of intent made by Editor‐in‐Chief Phil Thomas published either within or regarding the JLS, we present a map of the journal's role within, impact upon, and enduring contribution to UK socio‐legal studies. Finally, we discuss our results and propose future directions of the field.

Correlation-aware Graph Data Augmentation with Implicit and Explicit Neighbors

In recent years, there has been a significant surge in commercial demand for citation graph-based tasks, such as patent analysis, social network analysis, and recommendation systems. Graph Neural Networks (GNNs) are widely used for these tasks due to their remarkable performance in capturing topological graph information. However, GNNs’ output results are highly dependent on the composition of local neighbors within the topological structure. To address this issue, we identify two types of neighbors in a citation graph: explicit neighbors based on the topological structure and implicit neighbors based on node features. Our primary motivation is to clearly define and visualize these neighbors, emphasizing their importance in enhancing graph neural network performance. We propose a Correlation-aware Network (CNet) to re-organize the citation graph and learn more valuable informative representations by leveraging these implicit and explicit neighbors. Our approach aims to improve graph data augmentation and classification performance, with the majority of our focus on stating the importance of using these neighbors, while also introducing a new graph data augmentation method. We compare CNet with state-of-the-art (SOTA) GNNs and other graph data augmentation approaches acting on GNNs. Extensive experiments demonstrate that CNet effectively extracts more valuable informative representations from the citation graph, significantly outperforming baselines. The code is available on public GitHub. 1

Transfer operators on graphs: spectral clustering and beyond

Graphs and networks play an important role in modeling and analyzing complex interconnected systems such as transportation networks, integrated circuits, power grids, citation graphs, and biological and artificial neural networks. Graph clustering algorithms can be used to detect groups of strongly connected vertices and to derive coarse-grained models. We define transfer operators such as the Koopman operator and the Perron–Frobenius operator on graphs, study their spectral properties, introduce Galerkin projections of these operators, and illustrate how reduced representations can be estimated from data. In particular, we show that spectral clustering of undirected graphs can be interpreted in terms of eigenfunctions of the Koopman operator and propose novel clustering algorithms for directed graphs based on generalized transfer operators. We demonstrate the efficacy of the resulting algorithms on several benchmark problems and provide different interpretations of clusters.

CLUSTERING OF SCIENTISTS' PUBLICATIONS, CONSIDERING FINDING SIMILARITIES IN ABSTRACTS AND TEXTS OF PUBLICATIONS BASED ON N-GRAM ANALYSIS AND IDENTIFYING POTENTIAL PROJECT GROUPS

The article describes the solution to the problem of clustering scientists' publications, taking into account the finding of similarities in the annotations and texts of these publications based on n-grams of analysis and cross-references, as well as the tasks of identifying potential project groups for the implementation of research and educational projects based on the results of clustering. The selection of scientific partners in the world practice is done without a comprehensive assessment of their activities. Most of the well-known indexes for evaluating the research activities of scientists need to consider information about citations fully. The methods developed in the study for evaluating the scientific activities of scientists and universities, as well as methods for selecting scientific partners for the implementation of educational and scientific projects on a scientific basis, allow us to organize the influential work of universities qualitatively. In the article, a probabilistic thematic model is constructed that allows the clustering of scientists' publications in scientific fields, considering the citation network, which is an important step in solving the problem of identifying subject scientific spaces. As a result of constructing the model, the problem of increasing instability of clustering of the citation graph due to a decrease in the number of clusters has been solved. The main objective of this work is to address the challenge of selecting suitable partners for collaboration in scientific and educational projects. To achieve this, a method for choosing project executors has been developed, which employs fuzzy logical inference to harmonize expert opinions regarding candidate requirements. This approach helps facilitate the multi-criteria selection of potential partners for scientific and educational projects. In addition to the method, various software modules have been created as part of this research. These modules are designed for the automated collection of information on the publications and citation records of scientists through international scientometric databases. They also encompass a visualization module and a user interface that aids in evaluating the scientific activities of university teaching staff. Choosing partners for grants or strategic collaborations, especially in the context of a globalized and highly mobile scientific community, remains a pertinent issue. The approach described in this research involves clustering the scientific publications of potential project partners. Furthermore, it incorporates conducting comparative citation analyses of these publications and establishing proximity based on n-gram annotation analysis. These methods provide a scientific basis for making informed choices when selecting partners, which is crucial for initiating and advancing research projects. Consequently, the selection of partners for forming research project teams is an immediate and pressing task.

The role of lifelong machine learning in bridging the gap between human and machine learning: A scientometric analysis

AbstractDue to advancements in data collection, storage, and processing techniques, machine learning has become a thriving and dominant paradigm. However, one of its main shortcomings is that the classical machine learning paradigm acts in isolation without utilizing the knowledge gained through learning from related tasks in the past. To circumvent this, the concept of Lifelong Machine Learning (LML) has been proposed, with the goal of mimicking how humans learn and acquire cognition. Human learning research has revealed that the brain connects previously learned information while learning new information from a single or small number of examples. Similarly, an LML system continually learns by storing and applying acquired information. Starting with an analysis of how the human brain learns, this paper shows that the LML framework shares a functional structure with the brain when it comes to solving new problems using previously learned information. It also provides a description of the LML framework, emphasizing its similarities to human brain learning. It also provides citation graph generation and scientometric analysis algorithms for the LML literatures, including information about the datasets and evaluation metrics that have been used in the empirical evaluation of LML systems. Finally, it presents outstanding issues and possible future research directions in the field of LML.This article is categorized under: Technologies > Machine Learning

A large-scale dataset of patient summaries for retrieval-based clinical decision support systems

Retrieval-based Clinical Decision Support (ReCDS) can aid clinical workflow by providing relevant literature and similar patients for a given patient. However, the development of ReCDS systems has been severely obstructed by the lack of diverse patient collections and publicly available large-scale patient-level annotation datasets. In this paper, we collect a novel dataset of patient summaries and relations called PMC-Patients to benchmark two ReCDS tasks: Patient-to-Article Retrieval (ReCDS-PAR) and Patient-to-Patient Retrieval (ReCDS-PPR). Specifically, we extract patient summaries from PubMed Central articles using simple heuristics and utilize the PubMed citation graph to define patient-article relevance and patient-patient similarity. PMC-Patients contains 167k patient summaries with 3.1 M patient-article relevance annotations and 293k patient-patient similarity annotations, which is the largest-scale resource for ReCDS and also one of the largest patient collections. Human evaluation and analysis show that PMC-Patients is a diverse dataset with high-quality annotations. We also implement and evaluate several ReCDS systems on the PMC-Patients benchmarks to show its challenges and conduct several case studies to show the clinical utility of PMC-Patients.

Recent Advances in Text Analysis

Text analysis is an interesting research area in data science and has various applications, such as in artificial intelligence, biomedical research, and engineering. We review popular methods for text analysis, ranging from topic modeling to the recent neural language models. In particular, we review Topic-SCORE, a statistical approach to topic modeling, and discuss how to use it to analyze the Multi-Attribute Data Set on Statisticians (MADStat), a data set on statistical publications that we collected and cleaned. The application of Topic-SCORE and other methods to MADStat leads to interesting findings. For example, we identified 11 representative topics in statistics. For each journal, the evolution of topic weights over time can be visualized, and these results are used to analyze the trends in statistical research. In particular, we propose a new statistical model for ranking the citation impacts of 11 topics, and we also build a cross-topic citation graph to illustrate how research results on different topics spread to one another. The results on MADStat provide a data-driven picture of the statistical research from 1975 to 2015, from a text analysis perspective.

A Comparative Analysis of Community Detection Agglomerative Technique Algorithms and Metrics on Citation Network

Social Network Analysis is a discipline that represents social relationships as a network of nodes and edges. The construction of social network with clusters will contribute in sharing the common characteristics or behaviour of a group. Partitioning the graph into modules is said to be a community. Communities are meant to symbolize actual social groups that share common characteristics. Citation network is one of the social networks with directed graphs where one paper will cite another paper and so on. Citation networks will assist the researcher in choosing research directions and evaluating research impacts. By constructing the citation networks with communities will direct the user to identify the similarity of documents which are interrelated to one or more domains. This paper introduces the agglomerative technique algorithms and metrics to a directed graph which determines the most influential nodes and group of similar nodes. The two stages required to construct the communities are how to generate network with communities and how to quantify the network performance. The strength and a quality of a network is quantified in terms of metrics like modularity, normalized mutual information (NMI), betweenness centrality, and F-Measure. The suitable community detection techniques and metrics for a citation graph were introduced in this paper. In the field of community detection, it is common practice to categorize algorithms according to the mathematical techniques they employ, and then compare them on benchmark graphs featuring a particular type of assortative community structure. The algorithms are applied for a sample citation sub data is extracted from DBLP, ACM, MAG and some additional sources which is taken from and consists of 101 nodes (nc) with 621 edges € and formed 64 communities. The key attributes in dataset are id, title, abstract, references SLM uses local optimisation and scalability to improve community detection in complicated networks. Unlike traditional methods, the proposed LS-SLM algorithm is identified that the modularity is increased by 12.65%, NMI increased by 2.31%, betweenness centrality by 3.18% and F-Score by 4.05%. The SLM algorithm outperforms existing methods in finding significant and well-defined communities, making it a promising community detection breakthrough.

Detecting Pseudo-Manipulated Citations in Scientific Literature through Perturbations of the Citation Graph

Ensuring the integrity of scientific literature is essential for advancing knowledge and research. However, the credibility and trustworthiness of scholarly publications are compromised by manipulated citations. Traditional methods, such as manual inspection and basic statistical analyses, have limitations in detecting intricate patterns and subtle manipulations of citations. In recent years, network-based approaches have emerged as promising techniques for identifying and understanding citation manipulation. This study introduces a novel method to identify potential citation manipulation in academic papers using perturbations of a deep embedding model. The key idea is to reconstruct meaningful connections represented by citations within a network by exploring, to some extent, longer alternative paths. These indirect pathways enable the recovery of reliable citations while estimating their trustworthiness. The investigation takes a comprehensive approach to link prediction, leveraging the consistent behavior of prominent connections when exposed to network perturbations. Through numerical experiments, the method demonstrates a high capability to identify reliable citations as the core of the analyzed data and to raise suspicions about unreliable references that may have been manipulated. This research presents a refined method for tackling the urgent problem of citation manipulation in academic papers. It harnesses statistical sampling and graph-embedding techniques to evaluate the credibility of scholarly publications with a substantial assessment of the whole citation graph.

The evolution of scientific literature as metastable knowledge states.

The problem of identifying common concepts in the sciences and deciding when new ideas have emerged is an open one. Metascience researchers have sought to formalize principles underlying stages in the life cycle of scientific research, understand how knowledge is transferred between scientists and stakeholders, and explain how new ideas are generated and take hold. Here, we model the state of scientific knowledge immediately preceding new directions of research as a metastable state and the creation of new concepts as combinatorial innovation. Through a novel approach combining natural language clustering and citation graph analysis, we predict the evolution of ideas over time and thus connect a single scientific article to past and future concepts in a way that goes beyond traditional citation and reference connections.

Multiresolution equivariant graph variational autoencoder

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation. Our implementation is available at https://github.com/HyTruongSon/MGVAE.

CLP-GCN: Confidence and label propagation applied to Graph Convolutional Networks

Node classification is an important task in many graph-related applications. Recently, graph neural networks like Graph Convolutional Networks (GCNs) have provided low-dimensional informative representations of the nodes of the graphs. However, there are some issues with the application of GCNs in real-world problems. First, information sharing among nodes is limited to directly connected nodes at each layer of GCNs and the contribution of all neighbors of each node is the same in feature aggregation. Second, learning a new representation and training a classifier over this representation require a considerable amount of labeled nodes while there are few labeled nodes in many real world node classification tasks. To compensate for the lack of enough labeled data, in this paper, we propose a novel method for label propagation for GCNs. The main idea of this method, named CLP-GCN, is to propagate the confidence scores of the labels along with the pseudo-labels assigned to the nodes. Two closeness criteria are used to estimate the similarity of each pair of nodes and this similarity measure governs the label propagation from one node of the graph to its neighbors. The confidence of each pseudo-label is determined based on the confidences of the adjacent nodes with the same label. Moreover, the adjacency matrix of GCN is replaced with a more informative matrix representing the structural closeness of the nodes resulting in a more selective feature smoothing in this network. Comprehensive experiments on popular datasets like Citation, Co-authorship, Co-purchase, and knowledge graph datasets demonstrate the superiority of CLP-GCN over state-of-the-art methods.

Question Answer System: A State-of-Art Representation of Quantitative and Qualitative Analysis

Question Answer System (QAS) automatically answers the question asked in natural language. Due to the varying dimensions and approaches that are available, QAS has a very diverse solution space, and a proper bibliometric study is required to paint the entire domain space. This work presents a bibliometric and literature analysis of QAS. Scopus and Web of Science are two well-known research databases used for the study. A systematic analytical study comprising performance analysis and science mapping is performed. Recent research trends, seminal work, and influential authors are identified in performance analysis using statistical tools on research constituents. On the other hand, science mapping is performed using network analysis on a citation and co-citation network graph. Through this analysis, the domain’s conceptual evolution and intellectual structure are shown. We have divided the literature into four important architecture types and have provided the literature analysis of Knowledge Base (KB)-based and GNN-based approaches for QAS.

Citation of publications in the natural sciences in the long-term observation

The author examines the chronological structure of bibliographic references to scholarly publications in the Web of Science (WoS) journals, in the context of using bibliometric methods in library (for specifying terms of collection acquisitions and preservation) and information practices. Seven thematic domains (WoS’ Subject Areas) within the natural sciences are discussed. The specifics of publication «aging» (citation decrease in proportion to the distance from the publication date) depends on their subject area and country. The determinant para-meters are: time period (from the publication date) to the maximum yearly citation value, ramp time (stabilizing yearly citation), yearly citation level (percent of maximum level), dynamics of citation timetable in the long term (up to 40 years). The author demonstrates that the shape of citation graph depends on the subject area and virtually does not depend on the country of publication.In six of seven subject areas (mathematics excluding), time of achieving maximum of yearly citation makes 2–4 years. Ramp time period (constant yearly citation level) differs greatly (from 8 to 23 years). Ramp level differs greatly for different subject areas and, within one domain, for the countries from 12% to 63% of maximum yearly citation. The secondary citation is observed in many subject areas at the end of observation period. This phenomenon needs further research. The chronological structure of bibliographic references for Mmathematics differs significantly from the other six subject areas: the y early citation rises a long the longer period (over 40 years); however, the dynamics of citation graph cannot be observed due to the limited time period of the study.

DisenCite: Graph-Based Disentangled Representation Learning for Context-Specific Citation Generation

Citing and describing related literature are crucial to scientific writing. Many existing approaches show encouraging performance in citation recommendation, but are unable to accomplish the more challenging and onerous task of citation text generation. In this paper, we propose a novel disentangled representation based model DisenCite to automatically generate the citation text through integrating paper text and citation graph. A key novelty of our method compared with existing approaches is to generate context-specific citation text, empowering the generation of different types of citations for the same paper. In particular, we first build and make available a graph enhanced contextual citation dataset (GCite) with 25K edges in different types characterized by citation contained sections over 4.8K research papers. Based on this dataset, we encode each paper according to both textual contexts and structure information in the heterogeneous citation graph. The resulted paper representations are then disentangled by the mutual information regularization between this paper and its neighbors in graph. Extensive experiments demonstrate the superior performance of our method comparing to state-of-the-art approaches. We further conduct ablation and case studies to reassure that the improvement of our method comes from generating the context-specific citation through incorporating the citation graph.

Keywords-Driven Paper Recommendation Based on Mobile Edge Computing Environment Framework

In the cloud computing era, a paper recommender system is usually deployed on the cloud server and return recommendation results to readers directly. However, considering the paper recommender system, processing tremendous paper citation data on the cloud cannot provide fine-grained personalized and real-time recommendations for each reader because these recommended papers from the cloud are far from readers and probably not correlated strongly with each other for helping each reader research further and deeper in the interested field. Recently, the edge-cloud collaboration-based recommender system has been used for releasing parts of the cloud computing task to the edge and provides the recommendation near the client. Based on the edge computing recommender system, a keywords-driven and weight-aware paper recommendation approach is presented, namely, LP-PRk+ w (link prediction-paper recommendation), to enable intelligent, personalized, and efficient paper recommendation services in the mobile edge computing environment. Specifically, the whole paper recommendation process mainly covers two parts: optimizing the existing paper citation graph via introducing a weighted similarity (i.e., building a weighted paper correlation graph) and then recommending a set of correlated papers according to the weighted paper correlation graph and the users’ query keywords. Experiments on a real-world paper correlation dataset, Hep-Th, show the capability of our proposal for improving the paper recommendation performance and its superiority against other related solutions.

Towards establishing a research lineage via identification of significant citations

Abstract Finding the lineage of a research topic is crucial for understanding the prior state of the art and advancing scientific displacement. The deluge of scholarly articles makes it difficult to locate the most relevant previous work. It causes researchers to spend a considerable amount of time building up their literature list. Citations play a crucial role in discovering relevant literature. However, not all citations are created equal. The majority of the citations that a paper receives provide contextual and background information to the citing papers. In those cases, the cited paper is not central to the theme of citing papers. However, some papers build upon a given paper and further the research frontier. In those cases, the concerned cited paper plays a pivotal role in the citing paper. Hence, the nature of the citation that the former receives from the latter is significant. In this work, we discuss our investigations towards discovering significant citations of a given paper. We further show how we can leverage significant citations to build a research lineage via a significant citation graph. We demonstrate the efficacy of our idea with two real-life case studies. Our experiments yield promising results with respect to the current state of the art in classifying significant citations, outperforming the earlier ones by a relative margin of 20 points in terms of precision. We hypothesize that such an automated system can facilitate relevant literature discovery and help identify knowledge flow for a particular category of papers.

Graph Neural Networks With Lifting-Based Adaptive Graph Wavelets

Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid transforms and cannot adapt to signals residing on graphs and tasks at hand. In this paper, we propose a novel class of graph neural networks that realizes graph filters with adaptive graph wavelets. Specifically, the adaptive graph wavelets are learned with neural network-parameterized lifting structures, where structure-aware attention-based lifting operations are developed to jointly consider graph structures and node features. We propose to lift based on diffusion wavelets to alleviate the structural information loss induced by partitioning non-bipartite graphs. By design, the locality and sparsity of the resulting wavelet transform as well as the scalability of the lifting structure are guaranteed. We further derive a soft-thresholding filtering operation by learning sparse graph representations in terms of the learned wavelets, yielding a localized, efficient, and scalable wavelet-based graph filters. To ensure that the learned graph representations are invariant to node permutations, a layer is employed at the input of the networks to reorder the nodes according to their local topology information. We evaluate the proposed networks in both node-level and graph-level representation learning tasks on benchmark citation and bioinformatics graph datasets. Extensive experiments demonstrate the superiority of the proposed networks over existing SGNNs in terms of accuracy, efficiency, and scalability.

SEAL: Semantically Enriched Authoring in LATEX—A Model for Scientific Discourse

Semantic tags can enrich citation graphs by inter-connecting papers with citation reasons. One of the best sources of knowledge to tell the reason for citation is the author himself. Integrating these reasons in an authoring system can help authors to choose a reason while citing. We examined various Human and Automatic authoring systems for integration of citation reasons. However, to the best of our knowledge, no such system exists that facilities authors to integrate the reasons while citing. Same is the case with Cite Packages. This research proposes integration of <i>CCRO</i>:Citations&#x2019; Context and Reasons Ontology&#x2019;s (Ihsan and Qadir, 2019) taxonomic hierarchy of reasons within document. We have developed a <i>CCRO</i> Package to semantically tag citations with reasons and to create an intra-discourse relation between research articles. Furthermore, embedding these structures within <i>RDF</i> Data Store enables the creation of knowledge graphs that become a foundation artifact for the Semantic &#x0026; Scientific Discourse.